Text Model¶

365 Models

Instruction Model¶

`AQ-MedAI/Diver-Retriever-0.6B`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	1.1 GB	2025-09-05	eng-Latn, zho-Hans

Citation

@misc{sun2026divermultistageapproachreasoningintensive,
      title={DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval},
      author={Duolin Sun and Meixiu Long and Dan Yang and Junjie Wang and Yecheng Luo and Yue Shen and Jian Wang and Hualei Zhou and Chunxiao Guo and Peng Wei and Jiahai Wang and Jinjie Gu},
      year={2026},
      eprint={2508.07995},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2508.07995},
}

`AQ-MedAI/Diver-Retriever-1.7B`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	2048	41.0K	3.2 GB	2025-10-13	eng-Latn, zho-Hans

Citation

@misc{sun2026divermultistageapproachreasoningintensive,
      title={DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval},
      author={Duolin Sun and Meixiu Long and Dan Yang and Junjie Wang and Yecheng Luo and Yue Shen and Jian Wang and Hualei Zhou and Chunxiao Guo and Peng Wei and Jiahai Wang and Jinjie Gu},
      year={2026},
      eprint={2508.07995},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2508.07995},
}

`AQ-MedAI/Diver-Retriever-4B`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2025-08-22	eng-Latn, zho-Hans

Citation

@misc{sun2026divermultistageapproachreasoningintensive,
      title={DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval},
      author={Duolin Sun and Meixiu Long and Dan Yang and Junjie Wang and Yecheng Luo and Yue Shen and Jian Wang and Hualei Zhou and Chunxiao Guo and Peng Wei and Jiahai Wang and Jinjie Gu},
      year={2026},
      eprint={2508.07995},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2508.07995},
}

`AQ-MedAI/Diver-Retriever-4B-1020`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2025-10-20	eng-Latn, zho-Hans

Citation

@misc{sun2026divermultistageapproachreasoningintensive,
      title={DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval},
      author={Duolin Sun and Meixiu Long and Dan Yang and Junjie Wang and Yecheng Luo and Yue Shen and Jian Wang and Hualei Zhou and Chunxiao Guo and Peng Wei and Jiahai Wang and Jinjie Gu},
      year={2026},
      eprint={2508.07995},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2508.07995},
}

`Alibaba-NLP/gte-Qwen1.5-7B-instruct`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	28.8 GB	2024-04-20	eng-Latn

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`Alibaba-NLP/gte-Qwen2-1.5B-instruct`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	8960	32.8K	6.6 GB	2024-07-29	eng-Latn

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`Alibaba-NLP/gte-Qwen2-7B-instruct`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	3584	32.8K	28.4 GB	2024-06-15	not specified

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`BAAI/bge-base-en`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	390.0 MB	2023-08-05	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-base-en-v1.5`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	390.0 MB	2023-09-11	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-base-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	390.0 MB	2023-08-05	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-base-zh-v1.5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	416.0 MB	2023-09-11	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-large-en`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2023-08-05	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-large-en-v1.5`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2023-09-12	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-large-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2023-08-02	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-large-zh-v1.5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2023-09-12	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-small-en`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2023-08-05	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-small-en-v1.5`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2023-09-12	eng-Latn

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-small-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	512	512	127.0 MB	2023-08-05	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-small-zh-v1.5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	512	512	91.0 MB	2023-09-12	zho-Hans

Citation

@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BMRetriever/BMRetriever-1B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
908.8M	2048	2.0K	3.4 GB	2024-04-29	eng-Latn

Citation

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

`BMRetriever/BMRetriever-2B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.5B	2048	8.2K	9.3 GB	2024-04-29	eng-Latn

Citation

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

`BMRetriever/BMRetriever-410M`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
353.8M	1024	2.0K	1.3 GB	2024-04-29	eng-Latn

Citation

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

`BMRetriever/BMRetriever-7B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	26.5 GB	2024-04-29	eng-Latn

Citation

@inproceedings{xu-etal-2024-bmretriever,
    title = "{BMR}etriever: Tuning Large Language Models as Better Biomedical Text Retrievers",
    author = "Xu, Ran and Shi, Wenqi and Yu, Yue and Zhuang, Yuchen and Zhu, Yanqiao and Wang, May Dongmei and Ho, Joyce C. and Zhang, Chao and Yang, Carl",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = "November",
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    pages = "22234--22254",
    url = "https://aclanthology.org/2024.emnlp-main.1241/"
}

`BeastyZ/e5-R-mistral-7b`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.2B	4096	32.8K	27.0 GB	2024-06-28	eng-Latn

`BidirLM/BidirLM-0.6B-Embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	8.2K	1.1 GB	2026-04-07	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (87)

Citation

@misc{boizard2026bidirlmtextomnimodalbidirectional,
      title={BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs},
      author={Nicolas Boizard and Théo Deschamps-Berger and Hippolyte Gisserot-Boukhlef and Céline Hudelot and Pierre Colombo},
      year={2026},
      eprint={2604.02045},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.02045},
}

`BidirLM/BidirLM-1.7B-Embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	2048	8.2K	3.2 GB	2026-04-07	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (87)

Citation

@misc{boizard2026bidirlmtextomnimodalbidirectional,
      title={BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs},
      author={Nicolas Boizard and Théo Deschamps-Berger and Hippolyte Gisserot-Boukhlef and Céline Hudelot and Pierre Colombo},
      year={2026},
      eprint={2604.02045},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.02045},
}

`BidirLM/BidirLM-1B-Embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
999.9M	1152	32.8K	1.9 GB	2026-04-07	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (87)

Citation

@misc{boizard2026bidirlmtextomnimodalbidirectional,
      title={BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs},
      author={Nicolas Boizard and Théo Deschamps-Berger and Hippolyte Gisserot-Boukhlef and Céline Hudelot and Pierre Colombo},
      year={2026},
      eprint={2604.02045},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.02045},
}

`BidirLM/BidirLM-270M-Embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
268.1M	640	32.8K	511.0 MB	2026-04-07	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (87)

Citation

@misc{boizard2026bidirlmtextomnimodalbidirectional,
      title={BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs},
      author={Nicolas Boizard and Théo Deschamps-Berger and Hippolyte Gisserot-Boukhlef and Céline Hudelot and Pierre Colombo},
      year={2026},
      eprint={2604.02045},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.02045},
}

`ByteDance-Seed/Seed1.5-Embedding`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	32.8K	not specified	2025-04-25	eng-Latn, zho-Hans

`Bytedance/Seed1.6-embedding-1215`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	32.8K	not specified	2025-12-15	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Cohere/Cohere-embed-english-light-v3.0`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	384	512	not specified	2023-11-02	eng-Latn

`Cohere/Cohere-embed-english-v3.0`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	512	not specified	2023-11-02	eng-Latn

`Cohere/Cohere-embed-multilingual-light-v3.0`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	384	512	not specified	2023-11-02	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (111)

`Cohere/Cohere-embed-multilingual-v3.0`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	512	not specified	not specified	2023-11-02	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (111)

`Cohere/Cohere-embed-v5.0-fast`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	8.2K	not specified	not specified	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (111)

`Cohere/Cohere-embed-v5.0-pro`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	8.2K	not specified	not specified	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (111)

`GeoGPT-Research-Project/GeoEmbedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	27.0 GB	2025-04-22	eng-Latn

`GritLM/GritLM-7B`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.2B	4096	32.8K	13.5 GB	2024-02-15	deu-Latn, eng-Latn, fra-Latn, ita-Latn, spa-Latn

Citation

@misc{muennighoff2024generative,
      title={Generative Representational Instruction Tuning},
      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
      year={2024},
      eprint={2402.09906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`GritLM/GritLM-8x7B`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
57.9B	32768	32.8K	87.0 GB	2024-02-15	deu-Latn, eng-Latn, fra-Latn, ita-Latn, spa-Latn

Citation

@misc{muennighoff2024generative,
      title={Generative Representational Instruction Tuning},
      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
      year={2024},
      eprint={2402.09906},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	512	1.8 GB	2024-10-23	eng-Latn, zho-Hans

Citation

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	512	1.8 GB	2024-12-26	eng-Latn, zho-Hans

Citation

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	512	942.0 MB	2025-06-25	eng-Latn, zho-Hans

Citation

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

`Hanno-Labs/dinghy-law-0.6b-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.8M	1024	32.8K	1.1 GB	2026-07-13	deu-Latn, eng-Latn, zho-Hans

`Hanno-Labs/dinghy-law-4b-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2026-07-22	deu-Latn, eng-Latn, zho-Hans

`Hanno-Labs/dinghy-law-8b-v1`¶

License: openmdw-1.1 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.0B	4096	8.2K	14.8 GB	2026-07-31	deu-Latn, eng-Latn, zho-Hans

`ICT-TIME-and-Querit/BOOM_4B_v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2026-01-31	ara-Arab, ben-Beng, deu-Latn, eng-Latn, fas-Arab, ... (18)

Citation

@article{zhang2026bagging,
  title={Bagging-Based Model Merging for Robust General Text Embeddings},
  author={Zhang, Hengran and Bi, Keping and Guo, Jiafeng and Zhang, Jiaming and Yang, Wenbo and Shi, Daiting and Cheng, Xueqi},
  journal={arXiv preprint arXiv:2602.05787},
  year={2026}
}

`ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2026-05-02	ara-Arab, ben-Beng, deu-Latn, eng-Latn, fas-Arab, ... (18)

Citation

@article{zhang2026bagging,
  title={Bagging-Based Model Merging for Robust General Text Embeddings},
  author={Zhang, Hengran and Bi, Keping and Guo, Jiafeng and Zhang, Jiaming and Yang, Wenbo and Shi, Daiting and Cheng, Xueqi},
  journal={arXiv preprint arXiv:2602.05787},
  year={2026}
}

`IEITYuan/Yuan-embedding-2.0-en`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	2.0K	2.2 GB	2025-11-27	eng-Latn

`KaLM-Embedding/KaLM-Reranker-V1-Large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	2560	131.1K	14.0 GB	2026-06-23	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-Reranker-V1-Large-R2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	2560	131.1K	14.0 GB	2026-09-08	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-Reranker-V1-Nano`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
786.0M	640	131.1K	1.5 GB	2026-06-23	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-Reranker-V1-Nano-R2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
786.0M	640	131.1K	1.5 GB	2026-09-08	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-Reranker-V1-Small`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.1B	1152	131.1K	3.9 GB	2026-06-23	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-Reranker-V1-Small-R2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.1B	1152	131.1K	3.9 GB	2026-09-08	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{zhao2026lycheererankerfastlateinteraction,
      title={Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking},
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Huiyao Chen and Shouzheng Huang and Xianhao Xiong and Danyu Tang and Xinshuo Hu and Guohong Fu and Meishan Zhang and Baotian Hu},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807},
}

`KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	512	1.8 GB	2025-09-30	eng-Latn, zho-Hans

Citation

@misc{zhao2025kalmembeddingv2,
      title={KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model},
      author={Xinping Zhao and Xinshuo Hu and Zifei Shan and Shouzheng Huang and Yao Zhou and Xin Zhang and Zetian Sun and Zhenyu Liu and Dongfang Li and Xinyuan Wei and Youcheng Pan and Yang Xiang and Meishan Zhang and Haofen Wang and Jun Yu and Baotian Hu and Min Zhang},
      year={2025},
      eprint={2506.20923},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.20923},
}

@misc{hu2025kalmembedding,
      title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
      author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
      year={2025},
      eprint={2501.01028},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.01028},
}

`Kingsoft-LLM/QZhou-Embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	3584	8.2K	14.1 GB	2025-08-24	eng-Latn, zho-Hans

Citation

@misc{yu2025qzhouembeddingtechnicalreport,
      title={QZhou-Embedding Technical Report},
      author={Peng Yu and En Xu and Bin Chen and Haibiao Chen and Yinfei Xu},
      year={2025},
      eprint={2508.21632},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.21632},
}

`Kingsoft-LLM/QZhou-Embedding-Zh`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	1792	8.2K	28.7 GB	2025-09-28	zho-Hans

Citation

@misc{yu2025qzhouembeddingtechnicalreport,
      title={QZhou-Embedding Technical Report},
      author={Peng Yu and En Xu and Bin Chen and Haibiao Chen and Yinfei Xu},
      year={2025},
      eprint={2508.21632},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.21632},
}

`KiteFishAI/Nano-Em1-0.6B-v2`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	41.0K	1.1 GB	2026-07-20	eng-Latn

`KiteFishAI/Nano-Em1-0.6B-v2.1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	41.0K	1.1 GB	2026-08-11	eng-Latn

`LingoIITGN/FlowVec-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	41.0K	14.1 GB	2026-09-08	asm-Beng, ben-Beng, brx-Deva, doi-Deva, guj-Gujr, ... (21)

`LingoIITGN/qwen-indic-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	41.0K	14.1 GB	2026-07-03	asm-Beng, ben-Beng, brx-Deva, doi-Deva, guj-Gujr, ... (21)

`Linq-AI-Research/Linq-Embed-Mistral`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	13.2 GB	2024-05-29	eng-Latn

`LiquidAI/LFM2.5-Embedding-350M`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
354.5M	1024	128.0K	676.0 MB	2026-06-18	ara-Arab, deu-Latn, eng-Latn, fra-Latn, ita-Latn, ... (11)

`ManiacLabs/miniac-embed`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	1024	512	127.0 MB	2026-02-19	eng-Latn

`McGill-NLP/AfriE5-Large-instruct`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
560.0M	1024	514	1.0 GB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

`McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
6.6B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
6.6B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	4096	8.2K	28.0 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-unsup-simcse`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	4096	8.2K	28.0 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.2B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.2B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-supervised`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	4096	32.8K	26.5 GB	2024-04-09	eng-Latn

Citation

@misc{behnamghader2024llm2veclargelanguagemodels,
      title={LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders},
      author={Parishad BehnamGhader and Vaibhav Adlakha and Marius Mosbach and Dzmitry Bahdanau and Nicolas Chapados and Siva Reddy},
      year={2024},
      eprint={2404.05961},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2404.05961},
}

`MongoDB/mdbr-leaf-ir`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	768	512	86.0 MB	2025-08-27	eng-Latn

Citation

@inproceedings{mdbr_leaf,
  address = {San Diego, California, United States},
  author = {Vujanic, Robin and R{\"u}ckstie{\ss}, Thomas},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2026.acl-long.2008},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-390-6},
  month = {jul},
  pages = {43362--43383},
  publisher = {Association for Computational Linguistics},
  title = {{LEAF}: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations},
  url = {https://aclanthology.org/2026.acl-long.2008/},
  year = {2026},
}

`MongoDB/mdbr-leaf-mt`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	1024	512	86.0 MB	2025-08-27	eng-Latn

Citation

@inproceedings{mdbr_leaf,
  address = {San Diego, California, United States},
  author = {Vujanic, Robin and R{\"u}ckstie{\ss}, Thomas},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2026.acl-long.2008},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-390-6},
  month = {jul},
  pages = {43362--43383},
  publisher = {Association for Computational Linguistics},
  title = {{LEAF}: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations},
  url = {https://aclanthology.org/2026.acl-long.2008/},
  year = {2026},
}

`NGA-KR/ko-embed-midm`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.3B	1792	512	8.6 GB	2026-10-27	eng-Latn, kor-Hang

`NGA-KR/ko-embed-v0`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
148.7M	768	512	284.0 MB	2026-09-10	eng-Latn, kor-Hang

`NovaSearch/jasper_en_vision_language_v1`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.6B	8960	131.1K	3.7 GB	2024-12-11	eng-Latn

Citation

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

`NovaSearch/stella_en_1.5B_v5`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	8960	131.1K	5.7 GB	2024-07-12	eng-Latn

Citation

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

`NovaSearch/stella_en_400M_v5`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
435.0M	4096	8.2K	1.6 GB	2024-07-12	eng-Latn

Citation

@misc{zhang2025jasperstelladistillationsota,
      title={Jasper and Stella: distillation of SOTA embedding models},
      author={Dun Zhang and Jiacheng Li and Ziyang Zeng and Fulong Wang},
      year={2025},
      eprint={2412.19048},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2412.19048},
}

`Octen/Octen-Embedding-0.6B`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	1.1 GB	2026-01-10	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/Octen-Embedding-4B`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2025-12-30	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/Octen-Embedding-4B-INT8`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	1024	32.8K	3.7 GB	2026-04-02	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/Octen-Embedding-8B`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	32.8K	14.1 GB	2025-12-23	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/Octen-Embedding-8B-INT8`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	1024	32.8K	7.0 GB	2026-01-10	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/octen-vl-embedding`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	32.0K	not specified	2026-05-15	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Octen/octen-vl-embedding-large`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	4096	32.0K	not specified	2026-05-15	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`Qwen/Qwen3-Embedding-0.6B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	1.1 GB	2025-06-05	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`Qwen/Qwen3-Embedding-4B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2025-06-05	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`Qwen/Qwen3-Embedding-8B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	32.8K	14.1 GB	2025-06-05	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`Qwen/Qwen3-Reranker-0.6B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	41.0K	1.1 GB	2025-05-29	not specified

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`Qwen/Qwen3-Reranker-4B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2025-06-03	not specified

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`Qwen/Qwen3-Reranker-8B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.2B	4096	41.0K	15.3 GB	2025-05-29	not specified

Citation

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}

`ReasonIR/ReasonIR-8B`¶

License: cc-by-nc-4.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	4096	131.1K	not specified	2025-04-29	eng-Latn

Citation

@article{shao2025reasonir,
      title={ReasonIR: Training Retrievers for Reasoning Tasks},
      author={Rulin Shao and Rui Qiao and Varsha Kishore and Niklas Muennighoff and Xi Victoria Lin and Daniela Rus and Bryan Kian Hsiang Low and Sewon Min and Wen-tau Yih and Pang Wei Koh and Luke Zettlemoyer},
      year={2025},
      journal={arXiv preprint arXiv:2504.20595},
      url={https://arxiv.org/abs/2504.20595},
}

`Rebine/Etsu-Embedding-0.8B-Memory`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
752.4M	1024	2.0K	1.5 GB	2026-10-03	cmn-Hans, eng-Latn

`Sailesh97/Hinvec`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
939.6M	2048	2.0K	3.6 GB	2025-06-19	eng-Latn, hin-Deva

`Salesforce/SFR-Embedding-2_R`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	13.2 GB	2024-06-14	eng-Latn

`Salesforce/SFR-Embedding-Code-2B_R`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.6B	2304	8.2K	4.9 GB	2025-01-17	eng-Latn

Citation

@article{liu2024codexembed,
  title={CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval},
  author={Liu, Ye and Meng, Rui and Jot, Shafiq and Savarese, Silvio and Xiong, Caiming and Zhou, Yingbo and Yavuz, Semih},
  journal={arXiv preprint arXiv:2411.12644},
  year={2024}
}

`Salesforce/SFR-Embedding-Mistral`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	13.2 GB	2024-01-24	eng-Latn

`SamilPwC-AXNode-GenAI/PwC-Embedding_expr`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	514	2.1 GB	2025-08-12	kor-Hang

`Singaraj/sante-embed`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	1536	512	2.9 GB	2026-09-15	ara-Arab, eng-Latn, fra-Latn, kor-Hang, pol-Latn, ... (9)

`Snowflake/snowflake-arctic-embed-l`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	1.2 GB	2024-04-12	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Snowflake/snowflake-arctic-embed-l-v2.0`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-12-04	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (74)

Citation

@article{yu2024arctic,
      title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
      author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
      journal={arXiv preprint arXiv:2412.04506},
      year={2024},
      eprint={2412.04506},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2412.04506}
}

`Snowflake/snowflake-arctic-embed-m`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	415.0 MB	2024-04-12	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Snowflake/snowflake-arctic-embed-m-long`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
137.0M	768	2.0K	522.0 MB	2024-04-12	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Snowflake/snowflake-arctic-embed-m-v1.5`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	415.0 MB	2024-07-08	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Snowflake/snowflake-arctic-embed-m-v2.0`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
305.0M	768	8.2K	1.1 GB	2024-12-04	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (74)

Citation

@article{yu2024arctic,
      title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
      author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
      journal={arXiv preprint arXiv:2412.04506},
      year={2024},
      eprint={2412.04506},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2412.04506}
}

`Snowflake/snowflake-arctic-embed-s`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2024-04-12	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Snowflake/snowflake-arctic-embed-xs`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	86.0 MB	2024-07-08	eng-Latn

Citation

@article{merrick2024embedding,
      title={Embedding And Clustering Your Data Can Improve Contrastive Pretraining},
      author={Merrick, Luke},
      journal={arXiv preprint arXiv:2407.18887},
      year={2024},
      eprint={2407.18887},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2407.18887}
}

`Tarka-AIR/Tarka-Embedding-150M-V1`¶

License: gemma • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
155.7M	768	2.0K	576.0 MB	2025-11-04	arb-Arab, deu-Latn, eng-Latn, fra-Latn, jpn-Jpan, ... (8)

Citation

@misc{tarka_ai_research_2025,
    author       = { Tarka AI Research },
    title        = { Tarka-Embedding-150M-V1 (Revision c5f4f43) },
    year         = 2025,
    url          = { https://huggingface.co/Tarka-AIR/Tarka-Embedding-150M-V1 },
    doi          = { 10.57967/hf/6875 },
    publisher    = { Hugging Face }
}

`Tarka-AIR/Tarka-Embedding-350M-V1`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
354.5M	1024	128.0K	676.0 MB	2025-11-11	arb-Arab, deu-Latn, eng-Latn, fra-Latn, jpn-Jpan, ... (8)

Citation

@misc{tarka_ai_research_2025,
    author       = { Tarka AI Research },
    title        = { Tarka-Embedding-350M-V1 (Revision f4b5de8) },
    year         = 2025,
    url          = { https://huggingface.co/Tarka-AIR/Tarka-Embedding-350M-V1 },
    doi          = { 10.57967/hf/6979 },
    publisher    = { Hugging Face }
}

`TencentBAC/Conan-embedding-v2`¶

License: apache-2.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	3584	32.8K	not specified	2025-04-10	eng-Latn, zho-Hans

`VPLabs/SearchMap_Preview`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
435.0M	4096	8.2K	1.6 GB	2025-03-05	eng-Latn

`WhereIsAI/UAE-Large-V1`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	1.2 GB	2023-12-04	eng-Latn

Citation

    @article{li2023angle,
      title={AnglE-optimized Text Embeddings},
      author={Li, Xianming and Li, Jing},
      journal={arXiv preprint arXiv:2309.12871},
      year={2023}
    }

`ai-forever/FRIDA`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
823.0M	1536	512	3.1 GB	2024-12-29	rus-Cyrl

`ai-forever/ru-en-RoSBERTa`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
404.0M	1024	512	1.5 GB	2024-07-29	rus-Cyrl

Citation

@inproceedings{snegirev2024russianfocusedembeddersexplorationrumteb,
  address = {Albuquerque, New Mexico},
  author = {Snegirev, Artem and Tikhonova, Maria and Anna, Maksimova and Fenogenova, Alena and Abramov, Aleksandr},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the {A}mericas Chapter of the {A}ssociation for {C}omputational {L}inguistics: Human Language Technologies (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.naacl-long.12},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  isbn = {979-8-89176-189-6},
  month = {apr},
  pages = {236--254},
  publisher = {Association for Computational Linguistics},
  title = {The {R}ussian-focused embedders' exploration: ru{MTEB} benchmark and {R}ussian embedding model design},
  url = {https://aclanthology.org/2025.naacl-long.12/},
  year = {2025},
}

`ai-sage/Giga-Embeddings-instruct`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.2B	2048	4.1K	12.6 GB	2025-09-23	eng-Latn, rus-Cyrl

`ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
10.5B	1536	8.2K	19.5 GB	2026-08-19	eng-Latn, rus-Cyrl

`ai-sage/Giga-Embeddings-instruct-3B-0826`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.2B	2048	8.2K	5.9 GB	2026-08-19	eng-Latn, rus-Cyrl

`ai-sage/Giga-Embeddings-instruct-480M-0826`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
483.7M	1024	8.2K	923.0 MB	2026-08-10	eng-Latn, rus-Cyrl

`annamodels/LGAI-Embedding-Preview`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	26.5 GB	2025-06-11	eng-Latn

Citation

@misc{choi2025lgaiembeddingpreviewtechnicalreport,
      title={LGAI-EMBEDDING-Preview Technical Report},
      author={Jooyoung Choi and Hyun Kim and Hansol Jang and Changwook Jun and Kyunghoon Bae and Hyewon Choi and Stanley Jungkyu Choi and Honglak Lee and Chulmin Yun},
      year={2025},
      eprint={2506.07438},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.07438},
}

`bedrock/cohere-embed-english-v3`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	512	not specified	2023-11-02	eng-Latn

`bedrock/cohere-embed-multilingual-v3`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	512	not specified	2023-11-02	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (111)

`bflhc/MoD-Embedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2025-12-14	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`castorini/repllama-v1-7b-lora-passage`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.0B	4096	4.1K	27.0 MB	2023-10-11	eng-Latn

Citation

@inproceedings{rankllama,
  author = {Ma, Xueguang and Wang, Liang and Yang, Nan and Wei, Furu and Lin, Jimmy},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657951},
  month = {July},
  pages = {2421–2425},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {Fine-Tuning LLaMA for Multi-Stage Text Retrieval},
  url = {https://doi.org/10.1145/3626772.3657951},
  year = {2024},
}

`cl-nagoya/ruri-base`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
111.2M	768	512	212.0 MB	2024-08-28	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-base-v2`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
111.2M	768	512	424.0 MB	2024-12-05	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-large`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
337.4M	1024	512	644.0 MB	2024-08-28	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-large-v2`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
337.4M	1024	512	1.3 GB	2024-12-06	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-small`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
68.1M	768	512	130.0 MB	2024-08-28	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-small-v2`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
68.1M	768	512	260.0 MB	2024-12-05	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-v3-130m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
132.1M	512	8.2K	504.0 MB	2025-04-09	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-v3-30m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
36.7M	256	8.2K	140.0 MB	2025-04-07	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-v3-310m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
314.6M	768	8.2K	1.2 GB	2025-04-09	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`cl-nagoya/ruri-v3-70m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
70.0M	256	8.2K	140.0 MB	2025-04-09	jpn-Jpan

Citation

@article{Ruri,
  author = {Tsukagoshi, Hayato and Sasano, Ryohei},
  doi = {10.5715/jnlp.33.591},
  issn = {2185-8314},
  journal = {Journal of Natural Language Processing},
  number = {2},
  pages = {591–629},
  publisher = {Association for Natural Language Processing},
  title = {Ruri: Japanese General Text Embeddings},
  url = {https://doi.org/10.5715/jnlp.33.591},
  volume = {33},
  year = {2026},
}

`clips/e5-base-trm-nl`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	514	237.0 MB	2025-09-23	nld-Latn

Citation

@inproceedings{banar2025mtebnle5nlembeddingbenchmark,
  address = {San Diego, California, United States},
  author = {Banar, Nikolay and Lotfi, Ehsan and Van Nooten, Jens and Arhiliuc, Cristina and Kliocaite, Marija and Daelemans, Walter},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
  doi = {10.18653/v1/2026.findings-acl.1236},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-395-1},
  month = {jul},
  pages = {24684--24709},
  publisher = {Association for Computational Linguistics},
  title = {{MTEB}-{NL} and {E}5-{NL}: Embedding Benchmark and Models for {D}utch},
  url = {https://aclanthology.org/2026.findings-acl.1236/},
  year = {2026},
}

`clips/e5-large-trm-nl`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
355.0M	1024	514	1.3 GB	2025-09-23	nld-Latn

Citation

@inproceedings{banar2025mtebnle5nlembeddingbenchmark,
  address = {San Diego, California, United States},
  author = {Banar, Nikolay and Lotfi, Ehsan and Van Nooten, Jens and Arhiliuc, Cristina and Kliocaite, Marija and Daelemans, Walter},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
  doi = {10.18653/v1/2026.findings-acl.1236},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-395-1},
  month = {jul},
  pages = {24684--24709},
  publisher = {Association for Computational Linguistics},
  title = {{MTEB}-{NL} and {E}5-{NL}: Embedding Benchmark and Models for {D}utch},
  url = {https://aclanthology.org/2026.findings-acl.1236/},
  year = {2026},
}

`clips/e5-small-trm-nl`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
40.8M	384	512	78.0 MB	2025-09-23	nld-Latn

Citation

@inproceedings{banar2025mtebnle5nlembeddingbenchmark,
  address = {San Diego, California, United States},
  author = {Banar, Nikolay and Lotfi, Ehsan and Van Nooten, Jens and Arhiliuc, Cristina and Kliocaite, Marija and Daelemans, Walter},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
  doi = {10.18653/v1/2026.findings-acl.1236},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-395-1},
  month = {jul},
  pages = {24684--24709},
  publisher = {Association for Computational Linguistics},
  title = {{MTEB}-{NL} and {E}5-{NL}: Embedding Benchmark and Models for {D}utch},
  url = {https://aclanthology.org/2026.findings-acl.1236/},
  year = {2026},
}

`codefuse-ai/C2LLM-0.5B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
497.3M	896	32.8K	948.0 MB	2025-12-22	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (8)

Citation

@misc{qin2025c2llmtechnicalreportnew,
    title={C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling},
    author={Jin Qin and Zihan Liao and Ziyin Zhang and Hang Yu and Peng Di and Rui Wang},
    year={2025},
    eprint={2512.21332},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2512.21332},
}

`codefuse-ai/C2LLM-7B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.7B	3584	32.8K	14.3 GB	2025-12-22	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (8)

Citation

@misc{qin2025c2llmtechnicalreportnew,
    title={C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling},
    author={Jin Qin and Zihan Liao and Ziyin Zhang and Hang Yu and Peng Di and Rui Wang},
    year={2025},
    eprint={2512.21332},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2512.21332},
}

`codefuse-ai/F2LLM-0.6B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	8.2K	1.1 GB	2025-09-18	eng-Latn

Citation

@article{2025F2LLM,
    title={F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    journal={CoRR},
    volume={abs/2510.02294},
    year={2025},
    url={https://doi.org/10.48550/arXiv.2510.02294},
    doi={10.48550/ARXIV.2510.02294},
    eprinttype={arXiv},
    eprint={2510.02294}
}

`codefuse-ai/F2LLM-1.7B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	2048	8.2K	3.2 GB	2025-09-18	eng-Latn

Citation

@article{2025F2LLM,
    title={F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    journal={CoRR},
    volume={abs/2510.02294},
    year={2025},
    url={https://doi.org/10.48550/arXiv.2510.02294},
    doi={10.48550/ARXIV.2510.02294},
    eprinttype={arXiv},
    eprint={2510.02294}
}

`codefuse-ai/F2LLM-4B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	8.2K	7.5 GB	2025-09-18	eng-Latn

Citation

@article{2025F2LLM,
    title={F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    journal={CoRR},
    volume={abs/2510.02294},
    year={2025},
    url={https://doi.org/10.48550/arXiv.2510.02294},
    doi={10.48550/ARXIV.2510.02294},
    eprinttype={arXiv},
    eprint={2510.02294}
}

`codefuse-ai/F2LLM-v2-0.6B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	41.0K	2.2 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-1.7B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	2048	41.0K	6.4 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-14B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
14.0B	5120	41.0K	52.1 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-160M`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
159.2M	640	41.0K	607.0 MB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-330M`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
334.3M	896	41.0K	1.2 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-4B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	15.0 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-80M`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
80.1M	320	41.0K	305.0 MB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`codefuse-ai/F2LLM-v2-8B`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	41.0K	28.2 GB	2026-03-09	afr-Latn, amh-Ethi, ara-Arab, azb-Arab, aze-Latn, ... (92)

Citation

@misc{f2llm-v2,
    title={F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World},
    author={Ziyin Zhang and Zihan Liao and Hang Yu and Peng Di and Rui Wang},
    year={2026},
    eprint={2603.19223},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2603.19223},
}

`deepvk/USER-base`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
427.0M	768	512	473.0 MB	2024-06-10	rus-Cyrl

`deepvk/USER2-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	568.0 MB	2025-04-19	rus-Cyrl

`deepvk/USER2-small`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
34.4M	384	8.2K	131.0 MB	2025-04-19	rus-Cyrl

`dmis-lab/UltraBERT-Embed-150M`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
151.0M	768	32.8K	576.0 MB	2026-10-10	eng-Latn

Citation

@misc{park2026ultrabertlimitbertpretraining,
      title={UltraBERT: Beyond the Limit of BERT Pre-Training},
      author={Jungwoo Park and Taewhoo Lee and Jaewoo Kang},
      year={2026},
      eprint={2610.15028},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2610.15028},
}

`dragonkue/multilingual-e5-small-ko`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2025-05-11	eng-Latn, kor-Hang

`dragonkue/multilingual-e5-small-ko-v2`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2025-06-10	eng-Latn, kor-Hang

`dragonkue/snowflake-arctic-embed-l-v2.0-ko`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2025-03-07	eng-Latn, kor-Hang

`emillykkejensen/EmbeddingGemma-Scandi-300m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
307.6M	768	2.0K	578.0 MB	2025-10-17	dan-Latn, nno-Latn, nob-Latn, nor-Latn, swe-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`emillykkejensen/Qwen3-Embedding-Scandi-0.6B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	2.2 GB	2025-10-17	dan-Latn, nno-Latn, nob-Latn, nor-Latn, swe-Latn

`emillykkejensen/mmBERTscandi-base-embedding`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	768	8.2K	1.1 GB	2025-10-17	dan-Latn, nno-Latn, nob-Latn, nor-Latn, swe-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`exp-models/dragonkue-KoEn-E5-Tiny`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
37.5M	384	512	143.0 MB	2025-05-13	eng-Latn, kor-Hang

`fyaronskiy/english_code_retriever`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	568.0 MB	2025-07-10	eng-Latn

`geevec-ai/geevec-embeddings-1.0`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	4096	32.8K	not specified	2026-04-02	not specified

`geevec-ai/geevec-embeddings-1.0-lite`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
366.0M	[256, 512, 1024, 2048, 4096]	32.8K	not specified	2026-04-02	not specified

`google/embeddinggemma-300m`¶

License: gemma • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
307.6M	768	2.0K	1.1 GB	2025-09-04	arb-Arab, ben-Beng, deu-Latn, eng-Latn, fin-Latn, ... (19)

Citation

@misc{vera2025embeddinggemmapowerfullightweighttext,
      title={EmbeddingGemma: Powerful and Lightweight Text Representations},
      author={Henrique Schechter Vera and Sahil Dua and Biao Zhang and Daniel Salz and Ryan Mullins and Sindhu Raghuram Panyam and Sara Smoot and Iftekhar Naim and Joe Zou and Feiyang Chen and Daniel Cer and Alice Lisak and Min Choi and Lucas Gonzalez and Omar Sanseviero and Glenn Cameron and Ian Ballantyne and Kat Black and Kaifeng Chen and Weiyi Wang and Zhe Li and Gus Martins and Jinhyuk Lee and Mark Sherwood and Juyeong Ji and Renjie Wu and Jingxiao Zheng and Jyotinder Singh and Abheesht Sharma and Divyashree Sreepathihalli and Aashi Jain and Adham Elarabawy and AJ Co and Andreas Doumanoglou and Babak Samari and Ben Hora and Brian Potetz and Dahun Kim and Enrique Alfonseca and Fedor Moiseev and Feng Han and Frank Palma Gomez and Gustavo Hernández Ábrego and Hesen Zhang and Hui Hui and Jay Han and Karan Gill and Ke Chen and Koert Chen and Madhuri Shanbhogue and Michael Boratko and Paul Suganthan and Sai Meher Karthik Duddu and Sandeep Mariserla and Setareh Ariafar and Shanfeng Zhang and Shijie Zhang and Simon Baumgartner and Sonam Goenka and Steve Qiu and Tanmaya Dabral and Trevor Walker and Vikram Rao and Waleed Khawaja and Wenlei Zhou and Xiaoqi Ren and Ye Xia and Yichang Chen and Yi-Ting Chen and Zhe Dong and Zhongli Ding and Francesco Visin and Gaël Liu and Jiageng Zhang and Kathleen Kenealy and Michelle Casbon and Ravin Kumar and Thomas Mesnard and Zach Gleicher and Cormac Brick and Olivier Lacombe and Adam Roberts and Qin Yin and Yunhsuan Sung and Raphael Hoffmann and Tris Warkentin and Armand Joulin and Tom Duerig and Mojtaba Seyedhosseini},
      year={2025},
      eprint={2509.20354},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.20354},
}

`google/gemini-embedding-001`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	3072	2.0K	not specified	2025-07-14	arb-Arab, ben-Beng, deu-Latn, eng-Latn, fin-Latn, ... (19)

Citation

@misc{lee2025geminiembeddinggeneralizableembeddings,
  title={Gemini Embedding: Generalizable Embeddings from Gemini},
  author={Jinhyuk Lee and Feiyang Chen and Sahil Dua and Daniel Cer and Madhuri Shanbhogue and Iftekhar Naim and Gustavo Hernández Ábrego and Zhe Li and Kaifeng Chen and Henrique Schechter Vera and Xiaoqi Ren and Shanfeng Zhang and Daniel Salz and Michael Boratko and Jay Han and Blair Chen and Shuo Huang and Vikram Rao and Paul Suganthan and Feng Han and Andreas Doumanoglou and Nithi Gupta and Fedor Moiseev and Cathy Yip and Aashi Jain and Simon Baumgartner and Shahrokh Shahi and Frank Palma Gomez and Sandeep Mariserla and Min Choi and Parashar Shah and Sonam Goenka and Ke Chen and Ye Xia and Koert Chen and Sai Meher Karthik Duddu and Yichang Chen and Trevor Walker and Wenlei Zhou and Rakesh Ghiya and Zach Gleicher and Karan Gill and Zhe Dong and Mojtaba Seyedhosseini and Yunhsuan Sung and Raphael Hoffmann and Tom Duerig},
  year={2025},
  eprint={2503.07891},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2503.07891},
}

`google/text-embedding-004`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	768	2.0K	not specified	2024-05-14	eng-Latn

`google/text-embedding-005`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	768	2.0K	not specified	2024-11-18	eng-Latn

`google/text-multilingual-embedding-002`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	768	2.0K	not specified	2024-05-14	arb-Arab, ben-Beng, deu-Latn, eng-Latn, fin-Latn, ... (19)

`infgrad/Jasper-Token-Compression-600M`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
607.3M	2048	32.8K	2.2 GB	2025-11-14	eng-Latn, zho-Hans

Citation

@misc{zhang2025jaspertokencompression600mtechnicalreport,
      title={Jasper-Token-Compression-600M Technical Report},
      author={Dun Zhang and Ziyang Zeng and Yudong Zhou and Shuyang Lu},
      year={2025},
      eprint={2511.14405},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2511.14405},
}

`infly/inf-retriever-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	3584	32.8K	13.2 GB	2024-12-24	eng-Latn, zho-Hans

Citation

@misc{infly-ai_2025,
  author       = {Junhan Yang and Jiahe Wan and Yichen Yao and Wei Chu and Yinghui Xu and Yuan Qi},
  title        = {inf-retriever-v1 (Revision 5f469d7)},
  year         = 2025,
  url          = {https://huggingface.co/infly/inf-retriever-v1},
  doi          = {10.57967/hf/4262},
  publisher    = {Hugging Face}
}

`infly/inf-retriever-v1-1.5b`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	1536	32.8K	2.9 GB	2025-02-08	eng-Latn, zho-Hans

Citation

@misc{infly-ai_2025,
  author       = {Junhan Yang and Jiahe Wan and Yichen Yao and Wei Chu and Yinghui Xu and Yuan Qi},
  title        = {inf-retriever-v1 (Revision 5f469d7)},
  year         = 2025,
  url          = {https://huggingface.co/infly/inf-retriever-v1},
  doi          = {10.57967/hf/4262},
  publisher    = {Hugging Face}
}

`intfloat/e5-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	418.0 MB	2022-12-26	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/e5-base-v2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	418.0 MB	2024-02-08	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/e5-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2022-12-26	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/e5-large-v2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	514	1.2 GB	2024-02-08	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/e5-mistral-7b-instruct`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	13.2 GB	2024-02-08	deu-Latn, eng-Latn, fra-Latn, ita-Latn, spa-Latn

Citation

    @inproceedings{wang2023improving,
  address = {Bangkok, Thailand},
  author = {Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  booktitle = {Proceedings of the 62nd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2024.acl-long.642},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {11897--11916},
  publisher = {Association for Computational Linguistics},
  title = {Improving Text Embeddings with Large Language Models},
  url = {https://aclanthology.org/2024.acl-long.642/},
  year = {2024},
}

    @article{wang2022text,
      title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
      author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
      journal={arXiv preprint arXiv:2212.03533},
      year={2022}
    }

`intfloat/e5-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.0M	384	512	127.0 MB	2024-02-08	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/e5-small-v2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.0M	384	512	127.0 MB	2024-02-08	eng-Latn

Citation

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

`intfloat/multilingual-e5-base`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`intfloat/multilingual-e5-large`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
560.0M	1024	514	2.1 GB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`intfloat/multilingual-e5-large-instruct`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
560.0M	1024	514	1.0 GB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
      title={Multilingual E5 Text Embeddings: A Technical Report},
      author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
      journal={arXiv preprint arXiv:2402.05672},
      year={2024}
    }

`intfloat/multilingual-e5-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.0M	384	512	449.0 MB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`jcorners/ingot-8b-r3`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	32.8K	not specified	2026-05-23	eng-Latn

`jinaai/jina-embeddings-v3`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
572.3M	1024	8.2K	1.1 GB	2024-09-18	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

    @misc{sturua2024jinaembeddingsv3multilingualembeddingstask,
      title={jina-embeddings-v3: Multilingual Embeddings With Task LoRA},
      author={Saba Sturua and Isabelle Mohr and Mohammad Kalim Akram and Michael Günther and Bo Wang and Markus Krimmel and Feng Wang and Georgios Mastrapas and Andreas Koukounas and Andreas Koukounas and Nan Wang and Han Xiao},
      year={2024},
      eprint={2409.10173},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2409.10173},
    }

`jinaai/jina-embeddings-v5-text-nano`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
211.8M	[32, 64, 128, 256, 512, 768]	8.2K	404.0 MB	2026-02-17	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{akram2026jinaembeddingsv5texttasktargetedembeddingdistillation,
      title={jina-embeddings-v5-text: Task-Targeted Embedding Distillation},
      author={Mohammad Kalim Akram and Saba Sturua and Nastia Havriushenko and Quentin Herreros and Michael Günther and Maximilian Werk and Han Xiao},
      year={2026},
      eprint={2602.15547},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.15547},
}

`jinaai/jina-embeddings-v5-text-small`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	[32, 64, 128, 256, 512, 768, 1024]	32.8K	1.1 GB	2026-02-17	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{akram2026jinaembeddingsv5texttasktargetedembeddingdistillation,
      title={jina-embeddings-v5-text: Task-Targeted Embedding Distillation},
      author={Mohammad Kalim Akram and Saba Sturua and Nastia Havriushenko and Quentin Herreros and Michael Günther and Maximilian Werk and Han Xiao},
      year={2026},
      eprint={2602.15547},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.15547},
}

`jxm/cde-small-v1`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
281.0M	768	512	1.0 GB	2024-09-24	eng-Latn

Citation

@inproceedings{morris2024contextualdocumentembeddings,
  archiveprefix = {arXiv},
  author = {John Xavier Morris and Alexander M Rush},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2410.02525},
  title = {Contextual Document Embeddings},
  url = {https://openreview.net/forum?id=Wqsk3FbD6D},
  year = {2025},
}

`jxm/cde-small-v2`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.0M	768	512	1.1 GB	2025-01-13	eng-Latn

Citation

@inproceedings{morris2024contextualdocumentembeddings,
  archiveprefix = {arXiv},
  author = {John Xavier Morris and Alexander M Rush},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2410.02525},
  title = {Contextual Document Embeddings},
  url = {https://openreview.net/forum?id=Wqsk3FbD6D},
  year = {2025},
}

`kazalbrur/bangla-embed-e5-small-banglish`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.0M	1024	512	450.0 MB	2026-06-23	ben-Beng, ben-Latn, eng-Latn

`litillabs/litil-embed-0.6b`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	1.1 GB	2026-09-13	deu-Latn, eng-Latn, zho-Hans

`litillabs/octen-law-8b-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	41.0K	14.1 GB	2026-08-25	deu-Latn, eng-Latn, zho-Hans

`llamaindex/vdr-2b-multi-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.2B	1536	32.8K	4.1 GB	2024-01-08	deu-Latn, eng-Latn, fra-Latn, ita-Latn, spa-Latn

`malteos/most-embed-de`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.1B	2048	32.8K	2.1 GB	2026-08-11	deu-Latn, eng-Latn

`manveertamber/cadet-embed-base-v1`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.0M	768	512	418.0 MB	2025-05-11	eng-Latn

Citation

@article{tamber2025conventionalcontrastivelearningfalls,
    title={Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data},
    author={Manveer Singh Tamber and Suleman Kazi and Vivek Sourabh and Jimmy Lin},
    journal={arXiv:2505.19274},
    year={2025}
}

`microsoft/harrier-oss-v1-0.6b`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	32.8K	1.1 GB	2026-03-27	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

`microsoft/harrier-oss-v1-270m`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
268.1M	640	32.8K	512.0 MB	2026-03-27	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

`microsoft/harrier-oss-v1-27b`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
27.0B	5376	131.1K	50.3 GB	2026-03-27	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

`mixedbread-ai/mxbai-embed-2d-large-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	768	512	not specified	2024-03-04	eng-Latn

`mixedbread-ai/mxbai-embed-large-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	639.0 MB	2024-03-07	eng-Latn

Citation

@article{li2023angle,
      title={AnglE-optimized Text Embeddings},
      author={Li, Xianming and Li, Jing},
      journal={arXiv preprint arXiv:2309.12871},
      year={2023}
    }

`mixedbread-ai/mxbai-embed-xsmall-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
24.1M	384	512	not specified	2024-08-13	eng-Latn

`mongodb/voyage-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	4.0K	not specified	2023-10-29	not specified

`mongodb/voyage-3`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2024-09-18	not specified

`mongodb/voyage-3-large`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2025-01-07	not specified

`mongodb/voyage-3-lite`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	512	32.0K	not specified	2024-09-18	not specified

`mongodb/voyage-3-m-exp`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
6.9B	2048	32.0K	not specified	2025-01-08	eng-Latn

`mongodb/voyage-3.5`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2025-01-21	not specified

`mongodb/voyage-3.5 (output_dtype=binary)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2025-01-21	not specified

`mongodb/voyage-3.5 (output_dtype=int8)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2025-01-21	not specified

`mongodb/voyage-4`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2026-01-15	not specified

`mongodb/voyage-4-large`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2026-01-15	not specified

`mongodb/voyage-4-large (embed_dim=2048)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	32.0K	not specified	2026-01-15	not specified

`mongodb/voyage-4-large (embed_dim=2048, evolved_prompts=True)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	2048	32.0K	not specified	2026-01-15	not specified

`mongodb/voyage-4-lite`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2026-01-15	not specified

`mongodb/voyage-4-nano`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
346.5M	2048	32.0K	661.0 MB	2026-01-15	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`mongodb/voyage-code-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1536	16.0K	not specified	2024-01-23	not specified

`mongodb/voyage-code-3`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2024-12-04	not specified

`mongodb/voyage-finance-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2024-05-30	not specified

`mongodb/voyage-large-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1536	16.0K	not specified	2023-10-29	not specified

`mongodb/voyage-large-2-instruct`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	16.0K	not specified	2024-05-05	not specified

`mongodb/voyage-law-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	16.0K	not specified	2024-04-15	not specified

`mongodb/voyage-multilingual-2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	32.0K	not specified	2024-06-10	not specified

`mteb/baseline-hybrid-dbsf-baseline-bm25s-multilingual-e5-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.0M	384	512	449.0 MB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`mteb/baseline-hybrid-rrf-baseline-bm25s-multilingual-e5-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.0M	384	512	449.0 MB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`mteb/baseline-hybrid-rsf-baseline-bm25s-multilingual-e5-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.0M	384	512	449.0 MB	2024-02-08	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

`nicher92/saga-embed_v1`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
404.2M	1024	512	2.1 GB	2025-01-09	dan-Latn, nor-Latn, swe-Latn

`nlpai-lab/KURE-v3`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.1B	2048	8.2K	2.1 GB	2026-10-20	eng-Latn, kor-Hang

`nlpai-lab/KoE5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	512	2.1 GB	2024-09-24	eng-Latn, kor-Hang

`nomic-ai/modernbert-embed-base`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	568.0 MB	2024-12-29	eng-Latn

Citation

@article{nussbaum2024nomic,
  archiveprefix = {arXiv},
  author = {Zach Nussbaum and John Xavier Morris and Andriy Mulyar and Brandon Duderstadt},
  eprint = {2402.01613},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {Reproducibility Certification},
  title = {Nomic Embed: Training a Reproducible Long Context Text Embedder},
  url = {https://openreview.net/forum?id=IPmzyQSiQE},
  year = {2025},
}

`nomic-ai/nomic-embed-code`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	3584	32.8K	26.3 GB	2025-03-24	eng-Latn

Citation

@inproceedings{suresh2025cornstackhighqualitycontrastivedata,
  archiveprefix = {arXiv},
  author = {Tarun Suresh and Revanth Gangi Reddy and Yifei Xu and Zach Nussbaum and Andriy Mulyar and Brandon Duderstadt and Heng Ji},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2412.01007},
  title = {Co{RNS}tack: High-Quality Contrastive Data for Better Code Retrieval and Reranking},
  url = {https://openreview.net/forum?id=iyJOUELYir},
  year = {2025},
}

`nomic-ai/nomic-embed-text-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.7M	768	8.2K	522.0 MB	2024-01-31	eng-Latn

Citation

@article{nussbaum2024nomic,
  archiveprefix = {arXiv},
  author = {Zach Nussbaum and John Xavier Morris and Andriy Mulyar and Brandon Duderstadt},
  eprint = {2402.01613},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {Reproducibility Certification},
  title = {Nomic Embed: Training a Reproducible Long Context Text Embedder},
  url = {https://openreview.net/forum?id=IPmzyQSiQE},
  year = {2025},
}

`nomic-ai/nomic-embed-text-v1-ablated`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.7M	768	8.2K	not specified	2024-01-15	eng-Latn

`nomic-ai/nomic-embed-text-v1-unsupervised`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.7M	768	8.2K	not specified	2024-01-15	eng-Latn

`nomic-ai/nomic-embed-text-v1.5`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.7M	768	8.2K	522.0 MB	2024-02-10	eng-Latn

Citation

@article{nussbaum2024nomic,
  archiveprefix = {arXiv},
  author = {Zach Nussbaum and John Xavier Morris and Andriy Mulyar and Brandon Duderstadt},
  eprint = {2402.01613},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {Reproducibility Certification},
  title = {Nomic Embed: Training a Reproducible Long Context Text Embedder},
  url = {https://openreview.net/forum?id=IPmzyQSiQE},
  year = {2025},
}

`nomic-ai/nomic-embed-text-v2-moe`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
475.3M	768	512	1.8 GB	2025-02-07	amh-Ethi, arb-Arab, bel-Cyrl, ben-Beng, bul-Cyrl, ... (98)

Citation

@misc{nussbaum2025trainingsparsemixtureexperts,
      title={Training Sparse Mixture Of Experts Text Embedding Models},
      author={Zach Nussbaum and Brandon Duderstadt},
      year={2025},
      eprint={2502.07972},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.07972},
}

`nvidia/NV-Embed-v1`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.8B	4096	32.8K	14.6 GB	2024-09-13	eng-Latn

Citation

@inproceedings{lee2025nvembedimprovedtechniquestraining,
  archiveprefix = {arXiv},
  author = {Chankyu Lee and Rajarshi Roy and Mengyao Xu and Jonathan Raiman and Mohammad Shoeybi and Bryan Catanzaro and Wei Ping},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2405.17428},
  title = {{NV}-Embed: Improved Techniques for Training {LLM}s as Generalist Embedding Models},
  url = {https://openreview.net/forum?id=lgsyLSsDRe},
  year = {2025},
}

`nvidia/NV-Embed-v2`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.8B	4096	32.8K	14.6 GB	2024-09-09	eng-Latn

Citation

@inproceedings{lee2025nvembedimprovedtechniquestraining,
  archiveprefix = {arXiv},
  author = {Chankyu Lee and Rajarshi Roy and Mengyao Xu and Jonathan Raiman and Mohammad Shoeybi and Bryan Catanzaro and Wei Ping},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2405.17428},
  title = {{NV}-Embed: Improved Techniques for Training {LLM}s as Generalist Embedding Models},
  url = {https://openreview.net/forum?id=lgsyLSsDRe},
  year = {2025},
}

`nvidia/llama-embed-nemotron-8b`¶

License: custom • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.5B	4096	32.8K	28.0 GB	2025-10-23	afr-Latn, amh-Ethi, ara-Arab, arq-Arab, ary-Arab, ... (66)

Citation

@misc{babakhin2025llamaembednemotron8buniversaltextembedding,
      title={Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks},
      author={Yauhen Babakhin and Radek Osmulski and Ronay Ak and Gabriel Moreira and Mengyao Xu and Benedikt Schifferer and Bo Liu and Even Oldridge},
      year={2025},
      eprint={2511.07025},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.07025},
}

`opensearch-project/opensearch-neural-sparse-encoding-doc-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
133.0M	30522	512	507.0 MB	2024-03-07	eng-Latn

`opensearch-project/opensearch-neural-sparse-encoding-doc-v2-distill`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
66.4M	30522	512	267.0 MB	2024-07-17	eng-Latn

`opensearch-project/opensearch-neural-sparse-encoding-doc-v2-mini`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	30522	512	86.0 MB	2024-07-18	eng-Latn

`opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
66.4M	30522	512	267.0 MB	2025-03-28	eng-Latn

`opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.8M	30522	8.2K	549.0 MB	2025-06-18	eng-Latn

`papr-ai/papr-embed-code-1-0.6b`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	2.2 GB	2026-10-22	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`papr-ai/papr-embed-code-1-4b`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	15.0 GB	2026-10-22	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

`petegordon/olmo3-embed-7b`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
6.9B	4096	512	12.8 GB	2026-10-14	eng-Latn

`qihoo360/Zhinao-ChineseModernBert-Embedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
227.0M	768	512	866.0 MB	2026-03-18	zho-Hans

`runelab-ai/kenning-turkish-legal-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
271.0M	[768, 512, 256, 128]	8.2K	1.0 GB	2026-10-07	eng-Latn, tur-Latn

`samaya-ai/RepLLaMA-reproduced`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.0B	4096	4.1K	27.0 MB	2024-09-15	eng-Latn

Citation

@inproceedings{rankllama,
  author = {Ma, Xueguang and Wang, Liang and Yang, Nan and Wei, Furu and Lin, Jimmy},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657951},
  month = {July},
  pages = {2421–2425},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {Fine-Tuning LLaMA for Multi-Stage Text Retrieval},
  url = {https://doi.org/10.1145/3626772.3657951},
  year = {2024},
}

`samaya-ai/promptriever-llama2-7b-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.0B	4096	4.1K	26.1 GB	2024-09-15	eng-Latn

Citation

@inproceedings{weller2024promptriever,
  archiveprefix = {arXiv},
  author = {Orion Weller and Benjamin Van Durme and Dawn Lawrie and Ashwin Paranjape and Yuhao Zhang and Jack Hessel},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2409.11136},
  title = {Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models},
  url = {https://openreview.net/forum?id=odvSjn416y},
  year = {2025},
}

`samaya-ai/promptriever-llama3.1-8b-instruct-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.0B	4096	8.2K	29.8 GB	2024-09-15	eng-Latn

Citation

@inproceedings{weller2024promptriever,
  archiveprefix = {arXiv},
  author = {Orion Weller and Benjamin Van Durme and Dawn Lawrie and Ashwin Paranjape and Yuhao Zhang and Jack Hessel},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2409.11136},
  title = {Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models},
  url = {https://openreview.net/forum?id=odvSjn416y},
  year = {2025},
}

`samaya-ai/promptriever-llama3.1-8b-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.0B	4096	8.2K	29.8 GB	2024-09-15	eng-Latn

Citation

@inproceedings{weller2024promptriever,
  archiveprefix = {arXiv},
  author = {Orion Weller and Benjamin Van Durme and Dawn Lawrie and Ashwin Paranjape and Yuhao Zhang and Jack Hessel},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2409.11136},
  title = {Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models},
  url = {https://openreview.net/forum?id=odvSjn416y},
  year = {2025},
}

`samaya-ai/promptriever-mistral-v0.1-7b-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.0B	4096	4.1K	26.1 GB	2024-09-15	eng-Latn

Citation

@inproceedings{weller2024promptriever,
  archiveprefix = {arXiv},
  author = {Orion Weller and Benjamin Van Durme and Dawn Lawrie and Ashwin Paranjape and Yuhao Zhang and Jack Hessel},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2409.11136},
  title = {Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models},
  url = {https://openreview.net/forum?id=odvSjn416y},
  year = {2025},
}

`sbintuitions/sarashina-embedding-v2-1b`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.2B	1792	8.2K	4.6 GB	2025-07-30	jpn-Jpan

`sergeyzh/BERTA`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
128.0M	768	512	489.0 MB	2025-03-10	rus-Cyrl

`sergeyzh/rubert-mini-frida`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
32.3M	312	2.0K	123.0 MB	2025-03-02	rus-Cyrl

`sionic-ai/comsat-embed-ja-0.3b-preview`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
314.6M	768	8.2K	1.2 GB	2026-07-02	jpn-Jpan

`sionic-ai/comsat-embed-ja-8b-preview`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	8.2K	14.1 GB	2026-07-03	eng-Latn, jpn-Jpan

`sionic-ai/comsat-embed-ko-8b-preview`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	8.2K	14.1 GB	2026-07-02	eng-Latn, kor-Hang

`telepix/PIXIE-Rune-v1.0`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	6.1K	2.1 GB	2026-01-15	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (74)

Citation

@article{yu2024arctic,
      title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
      author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
      journal={arXiv preprint arXiv:2412.04506},
      year={2024},
      eprint={2412.04506},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2412.04506}
}

`telepix/PIXIE-Rune-v1.5`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2026-04-22	eng-Latn, kor-Hang

`tencent/KaLM-Embedding-Gemma3-12B-2511`¶

License: not specified • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
11.8B	3840	32.8K	43.8 GB	2025-11-06	not specified

Citation

@misc{zhao2025kalmembeddingv2,
      title={KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model},
      author={Xinping Zhao and Xinshuo Hu and Zifei Shan and Shouzheng Huang and Yao Zhou and Xin Zhang and Zetian Sun and Zhenyu Liu and Dongfang Li and Xinyuan Wei and Youcheng Pan and Yang Xiang and Meishan Zhang and Haofen Wang and Jun Yu and Baotian Hu and Min Zhang},
      year={2025},
      eprint={2506.20923},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.20923},
}

@misc{hu2025kalmembedding,
      title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
      author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
      year={2025},
      eprint={2501.01028},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.01028},
}

`tencent/Youtu-Embedding`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.7B	2048	8.2K	not specified	2025-09-28	zho-Hans

Citation

@misc{zhang2025codiemb,
  title={CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity},
  author={Zhang, Bowen and Song, Zixin and Chen, Chunquan and Zhang, Qian-Wen and Yin, Di and Sun, Xing},
  year={2025},
  eprint={2508.11442},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2508.11442},
}

`yale-nlp/RTriever-4B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2026-04-30	eng-Latn

Citation

@inproceedings{zhao-etal-2026-rethinking,
    title = "Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems",
    author = "Zhao, Yilun  and
      Wei, Jinbiao  and
      Song, Tingyu  and
      Zhang, Siyue  and
      Zhao, Chen  and
      Cohan, Arman",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.acl-long.1705/",
    doi = "10.18653/v1/2026.acl-long.1705",
    pages = "36776--36806",
    ISBN = "979-8-89176-390-6",
}

`yibinlei/LENS-d4000`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4000	32.8K	26.5 GB	2025-01-17	not specified

Citation

@inproceedings{lei2025lens,
  address = {Vienna, Austria},
  author = {Lei, Yibin and Shen, Tao and Cao, Yu and Yates, Andrew},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.930},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {18986--19001},
  publisher = {Association for Computational Linguistics},
  title = {Enhancing Lexicon-Based Text Embeddings with Large Language Models},
  url = {https://aclanthology.org/2025.acl-long.930/},
  year = {2025},
}

`yibinlei/LENS-d8000`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	8000	32.8K	26.5 GB	2025-01-17	not specified

Citation

@inproceedings{lei2025lens,
  address = {Vienna, Austria},
  author = {Lei, Yibin and Shen, Tao and Cao, Yu and Yates, Andrew},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.930},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {18986--19001},
  publisher = {Association for Computational Linguistics},
  title = {Enhancing Lexicon-Based Text Embeddings with Large Language Models},
  url = {https://aclanthology.org/2025.acl-long.930/},
  year = {2025},
}

`zeta-alpha-ai/Zeta-Alpha-E5-Mistral`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	13.2 GB	2024-08-30	eng-Latn

Non-instruction Model¶

`AITeamVN/Vietnamese_Embedding`¶

License: cc-by-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-03-17	vie-Latn

`Alibaba-NLP/gte-base-en-v1.5`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
136.8M	768	8.2K	not specified	2024-06-20	eng-Latn

Citation

@inproceedings{zhang2024mgte,
  address = {Miami, Florida, US},
  author = {Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and Zhang, Meishan and Li, Wenjie and Zhang, Min},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  doi = {10.18653/v1/2024.emnlp-industry.103},
  editor = {Dernoncourt, Franck and Preo{\c{t}}iuc-Pietro, Daniel and Shimorina, Anastasia},
  month = {nov},
  pages = {1393--1412},
  publisher = {Association for Computational Linguistics},
  title = {{mGTE}: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
  url = {https://aclanthology.org/2024.emnlp-industry.103/},
  year = {2024},
}
@misc{li2023towards,
  title={Towards General Text Embeddings with Multi-stage Contrastive Learning},
  author={Zehan Li and Xin Zhang and Yanzhao Zhang and Dingkun Long and Pengjun Xie and Meishan Zhang},
  year={2023},
  eprint={2308.03281},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2308.03281},
}

`Alibaba-NLP/gte-modernbert-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	284.0 MB	2025-01-21	eng-Latn

Citation

@inproceedings{zhang2024mgte,
  address = {Miami, Florida, US},
  author = {Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and Zhang, Meishan and Li, Wenjie and Zhang, Min},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  doi = {10.18653/v1/2024.emnlp-industry.103},
  editor = {Dernoncourt, Franck and Preo{\c{t}}iuc-Pietro, Daniel and Shimorina, Anastasia},
  month = {nov},
  pages = {1393--1412},
  publisher = {Association for Computational Linguistics},
  title = {{mGTE}: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
  url = {https://aclanthology.org/2024.emnlp-industry.103/},
  year = {2024},
}

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`Alibaba-NLP/gte-multilingual-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
305.4M	768	8.2K	582.0 MB	2024-07-20	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@inproceedings{zhang2024mgte,
  address = {Miami, Florida, US},
  author = {Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and Zhang, Meishan and Li, Wenjie and Zhang, Min},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  doi = {10.18653/v1/2024.emnlp-industry.103},
  editor = {Dernoncourt, Franck and Preo{\c{t}}iuc-Pietro, Daniel and Shimorina, Anastasia},
  month = {nov},
  pages = {1393--1412},
  publisher = {Association for Computational Linguistics},
  title = {{mGTE}: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
  url = {https://aclanthology.org/2024.emnlp-industry.103/},
  year = {2024},
}

`BAAI/bge-en-icl`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	32.8K	26.5 GB	2024-07-25	eng-Latn

Citation

    @misc{li2024makingtextembeddersfewshot,
      title={Making Text Embedders Few-Shot Learners},
      author={Chaofan Li and MingHao Qin and Shitao Xiao and Jianlyu Chen and Kun Luo and Yingxia Shao and Defu Lian and Zheng Liu},
      year={2024},
      eprint={2409.15700},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2409.15700},
}

`BAAI/bge-m3`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
568.0M	1024	8.2K	2.1 GB	2024-06-28	afr-Latn, amh-Ethi, ast-Latn, azj-Latn, azj-Latn, ... (29)

Citation

@inproceedings{bge-m3,
  address = {Bangkok, Thailand},
  author = {Chen, Jianlyu and Xiao, Shitao and Zhang, Peitian and Luo, Kun and Lian, Defu and Liu, Zheng},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2024},
  doi = {10.18653/v1/2024.findings-acl.137},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {2318--2335},
  publisher = {Association for Computational Linguistics},
  title = {{M}3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
  url = {https://aclanthology.org/2024.findings-acl.137/},
  year = {2024},
}

`BAAI/bge-m3-unsupervised`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
568.0M	1024	8.2K	2.1 GB	2024-01-30	afr-Latn, amh-Ethi, ast-Latn, azj-Latn, azj-Latn, ... (29)

Citation

@inproceedings{bge-m3,
  address = {Bangkok, Thailand},
  author = {Chen, Jianlyu and Xiao, Shitao and Zhang, Peitian and Luo, Kun and Lian, Defu and Liu, Zheng},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2024},
  doi = {10.18653/v1/2024.findings-acl.137},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {2318--2335},
  publisher = {Association for Computational Linguistics},
  title = {{M}3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
  url = {https://aclanthology.org/2024.findings-acl.137/},
  year = {2024},
}

`BAAI/bge-multilingual-gemma2`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
9.2B	3584	8.2K	34.4 GB	2024-07-25	eng-Latn, fra-Latn, jpn-Jpan, jpn-Latn, kor-Hang, ... (7)

Citation

@inproceedings{bge-m3,
  address = {Bangkok, Thailand},
  author = {Chen, Jianlyu and Xiao, Shitao and Zhang, Peitian and Luo, Kun and Lian, Defu and Liu, Zheng},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2024},
  doi = {10.18653/v1/2024.findings-acl.137},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {2318--2335},
  publisher = {Association for Computational Linguistics},
  title = {{M}3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
  url = {https://aclanthology.org/2024.findings-acl.137/},
  year = {2024},
}


@inproceedings{xiao2024cpackpackedresourcesgeneral,
  author = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas and Lian, Defu and Nie, Jian-Yun},
  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  collection = {SIGIR 2024},
  doi = {10.1145/3626772.3657878},
  month = {July},
  pages = {641–649},
  publisher = {ACM},
  series = {SIGIR 2024},
  title = {C-Pack: Packed Resources For General Chinese Embeddings},
  url = {https://doi.org/10.1145/3626772.3657878},
  year = {2024},
}

`BAAI/bge-reranker-v2-m3`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	2.1 GB	2024-06-24	ara-Arab, ben-Beng, dan-Latn, deu-Latn, eng-Latn, ... (32)

Citation

@inproceedings{li2023making,
  address = {Bangkok, Thailand},
  author = {Li, Chaofan and Liu, Zheng and Xiao, Shitao and Shao, Yingxia and Lian, Defu},
  booktitle = {Proceedings of the 62nd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2024.acl-long.191},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {3490--3500},
  publisher = {Association for Computational Linguistics},
  title = {{L}lama2{V}ec: Unsupervised Adaptation of Large Language Models for Dense Retrieval},
  url = {https://aclanthology.org/2024.acl-long.191/},
  year = {2024},
}
    @inproceedings{bge-m3,
  address = {Bangkok, Thailand},
  author = {Chen, Jianlyu and Xiao, Shitao and Zhang, Peitian and Luo, Kun and Lian, Defu and Liu, Zheng},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2024},
  doi = {10.18653/v1/2024.findings-acl.137},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  month = {aug},
  pages = {2318--2335},
  publisher = {Association for Computational Linguistics},
  title = {{M}3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
  url = {https://aclanthology.org/2024.findings-acl.137/},
  year = {2024},
}

`BorisTM/starse`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
61.5M	512	Infinite	8.0 MB	2026-06-25	rus-Cyrl

`ByteDance/ListConRanker`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
401.0M	1024	512	1.2 GB	2024-12-11	zho-Hans

Citation

@article{liu2025listconranker,
  title={ListConRanker: A Contrastive Text Reranker with Listwise Encoding},
  author={Liu, Junlong and Ma, Yue and Zhao, Ruihui and Zheng, Junhao and Ma, Qianli and Kang, Yangyang},
  journal={arXiv preprint arXiv:2501.07111},
  year={2025}
}

`Classical/Yinka`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	1024	512	1.2 GB	2024-01-09	zho-Hans

`DMetaSoul/Dmeta-embedding-zh-small`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
74.2M	768	1.0K	283.0 MB	2024-03-25	zho-Hans

`DMetaSoul/sbert-chinese-general-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.3M	128	512	not specified	2022-03-25	zho-Hans

`DataScience-UIBK/uibk-embedding-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
179.0M	128	2.0K	683.0 MB	2026-10-10	eng-Latn

`DeepPavlov/distilrubert-small-cased-conversational`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
107.0M	768	512	408.0 MB	2022-06-28	rus-Cyrl

Citation

@inproceedings{https://doi.org/10.48550/arxiv.2205.02340,
  author = {Kolesnikova, Alina and Kuratov, Yuri and Konovalov, Vasily and Mikhail, Mikhail},
  booktitle = {Computational Linguistics and Intellectual Technologies},
  doi = {10.28995/2075-7182-2022-21-295-310},
  month = {June},
  pages = {295–310},
  publisher = {RSUH},
  title = {Knowledge Distillation of Russian Language Models with Reduction of Vocabulary},
  url = {https://doi.org/10.28995/2075-7182-2022-21-295-310},
  year = {2022},
}

`DeepPavlov/rubert-base-cased`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	768	512	4.8 GB	2020-03-04	rus-Cyrl

Citation

@misc{kuratov2019adaptationdeepbidirectionalmultilingual,
      title={Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language},
      author={Yuri Kuratov and Mikhail Arkhipov},
      year={2019},
      eprint={1905.07213},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/1905.07213},
    }

`DeepPavlov/rubert-base-cased-sentence`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
107.0M	768	512	408.0 MB	2020-03-04	rus-Cyrl

`FacebookAI/xlm-roberta-base`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	1.0 GB	2019-11-05	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@inproceedings{DBLP:journals/corr/abs-1911-02116,
  address = {Online},
  author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
  booktitle = {Proceedings of the 58th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics},
  doi = {10.18653/v1/2020.acl-main.747},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel},
  month = {jul},
  pages = {8440--8451},
  publisher = {Association for Computational Linguistics},
  title = {Unsupervised Cross-lingual Representation Learning at Scale},
  url = {https://aclanthology.org/2020.acl-main.747/},
  year = {2020},
}

`FacebookAI/xlm-roberta-large`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	512	2.1 GB	2019-11-05	afr-Latn, amh-Latn, ara-Latn, asm-Latn, aze-Latn, ... (99)

Citation

@inproceedings{DBLP:journals/corr/abs-1911-02116,
  address = {Online},
  author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
  booktitle = {Proceedings of the 58th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics},
  doi = {10.18653/v1/2020.acl-main.747},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel},
  month = {jul},
  pages = {8440--8451},
  publisher = {Association for Computational Linguistics},
  title = {Unsupervised Cross-lingual Representation Learning at Scale},
  url = {https://aclanthology.org/2020.acl-main.747/},
  year = {2020},
}

`Gameselo/STS-multilingual-mpnet-base-v2`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2024-06-07	not specified

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`GreenNode/GreenNode-Embedding-E5-Large-VN-V1`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
560.0M	1024	512	2.1 GB	2026-02-26	vie-Latn

`GreenNode/GreenNode-Embedding-KaLM-Mini-Instruct-VN-V1`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	32.8K	1.8 GB	2026-02-26	vie-Latn

`GreenNode/GreenNode-Embedding-Large-VN-Mixed-V1`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-04-11	vie-Latn

`GreenNode/GreenNode-Embedding-Large-VN-V1`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-04-11	vie-Latn

`HIT-TMG/KaLM-embedding-multilingual-mini-v1`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	512	1.8 GB	2024-08-27	eng-Latn, zho-Hans

Citation

@misc{hu2025kalmembedding,
  title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
  author={Xinshuo Hu and Zifei Shan and Xinping Zhao and Zetian Sun and Zhenyu Liu and Dongfang Li and Shaolin Ye and Xinyuan Wei and Qian Chen and Baotian Hu and Haofen Wang and Jun Yu and Min Zhang},
  year={2025},
  eprint={2501.01028},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.01028},
}

`Haon-Chen/speed-embedding-7b-instruct`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	not specified	32.8K	13.2 GB	2024-10-31	eng-Latn

Citation

@inproceedings{chen2024little,
  address = {Albuquerque, New Mexico},
  author = {Chen, Haonan and Wang, Liang and Yang, Nan and Zhu, Yutao and Zhao, Ziliang and Wei, Furu and Dou, Zhicheng},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the {A}mericas Chapter of the {A}ssociation for {C}omputational {L}inguistics: Human Language Technologies (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.naacl-long.64},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  isbn = {979-8-89176-189-6},
  month = {apr},
  pages = {1392--1411},
  publisher = {Association for Computational Linguistics},
  title = {Little Giants: Synthesizing High-Quality Embedding Data at Scale},
  url = {https://aclanthology.org/2025.naacl-long.64/},
  year = {2025},
}

`HooshvareLab/bert-base-parsbert-uncased`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
162.8M	768	512	621.0 MB	2021-05-19	fas-Arab

Citation

    @article{ParsBERT,
    title={ParsBERT: Transformer-based Model for Persian Language Understanding},
    author={Mehrdad Farahani, Mohammad Gharachorloo, Marzieh Farahani, Mohammad Manthouri},
    journal={ArXiv},
    year={2020},
    volume={abs/2005.12515}
}

`Hum-Works/lodestone-base-4096-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
137.4M	768	not specified	not specified	2023-08-25	eng-Latn

`IEITYuan/Yuan-embedding-2.0-zh`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
327.4M	1792	512	1.2 GB	2025-11-24	zho-Hans

`JMullings/spectral-embed-v1-140m`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
134.2M	2048	512	512.0 MB	2026-10-06	eng-Latn

`Jaume/gemma-2b-embeddings`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.5B	2048	8.2K	9.3 GB	2024-06-29	not specified

`KBLab/sentence-bert-swedish-cased`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.7M	768	384	476.0 MB	2023-01-11	swe-Latn

`KFST/XLMRoberta-en-da-sv-nb`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	1.0 GB	2022-02-22	dan-Latn, eng-Latn, nno-Latn, nob-Latn, swe-Latn

`KennethEnevoldsen/dfm-sentence-encoder-large`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
355.1M	1024	512	1.5 GB	2023-07-12	dan-Latn

Citation

@article{enevoldsenScandinavianEmbeddingBenchmarks2024,
    title = {The {Scandinavian} {Embedding} {Benchmarks}: {Comprehensive} {Assessment} of {Multilingual} and {Monolingual} {Text} {Embedding}},
    shorttitle = {The {Scandinavian} {Embedding} {Benchmarks}},
    url = {https://openreview.net/forum?id=pJl_i7HIA72},
    language = {en},
    urldate = {2024-04-12},
    author = {Enevoldsen, Kenneth and Kardos, Márton and Muennighoff, Niklas and Nielbo, Kristoffer},
    month = feb,
    year = {2024},
}

`KennethEnevoldsen/dfm-sentence-encoder-medium`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	512	475.0 MB	2023-07-12	dan-Latn

Citation

@article{enevoldsenScandinavianEmbeddingBenchmarks2024,
    title = {The {Scandinavian} {Embedding} {Benchmarks}: {Comprehensive} {Assessment} of {Multilingual} and {Monolingual} {Text} {Embedding}},
    shorttitle = {The {Scandinavian} {Embedding} {Benchmarks}},
    url = {https://openreview.net/forum?id=pJl_i7HIA72},
    language = {en},
    urldate = {2024-04-12},
    author = {Enevoldsen, Kenneth and Kardos, Márton and Muennighoff, Niklas and Nielbo, Kristoffer},
    month = feb,
    year = {2024},
}

`Kowshik24/bangla-sentence-transformer-ft-matryoshka-paraphrase-multilingual-mpnet-base-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	128	1.0 GB	2025-11-10	ben-Beng

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`Lajavaness/bilingual-embedding-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2024-06-26	not specified

Citation

    @inproceedings{DBLP:journals/corr/abs-1911-02116,
  address = {Online},
  author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
  booktitle = {Proceedings of the 58th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics},
  doi = {10.18653/v1/2020.acl-main.747},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel},
  month = {jul},
  pages = {8440--8451},
  publisher = {Association for Computational Linguistics},
  title = {Unsupervised Cross-lingual Representation Learning at Scale},
  url = {https://aclanthology.org/2020.acl-main.747/},
  year = {2020},
}

@inproceedings{reimers-2019-sentence-bert,
  author = {Reimers, Nils and Gurevych, Iryna},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing},
  month = {11},
  publisher = {Association for Computational Linguistics},
  title = {Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
  url = {https://arxiv.org/abs/1908.10084},
  year = {2019},
}

@article{thakur2020augmented,
  title={Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks},
  author={Thakur, Nandan and Reimers, Nils and Daxenberger, Johannes and Gurevych, Iryna},
  journal={arXiv e-prints},
  pages={arXiv--2010},
  year={2020}
}

`Lajavaness/bilingual-embedding-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	514	2.1 GB	2024-06-24	eng-Latn, fra-Latn

Citation

    @inproceedings{DBLP:journals/corr/abs-1911-02116,
  address = {Online},
  author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
  booktitle = {Proceedings of the 58th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics},
  doi = {10.18653/v1/2020.acl-main.747},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel},
  month = {jul},
  pages = {8440--8451},
  publisher = {Association for Computational Linguistics},
  title = {Unsupervised Cross-lingual Representation Learning at Scale},
  url = {https://aclanthology.org/2020.acl-main.747/},
  year = {2020},
}

@inproceedings{reimers-2019-sentence-bert,
  author = {Reimers, Nils and Gurevych, Iryna},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing},
  month = {11},
  publisher = {Association for Computational Linguistics},
  title = {Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
  url = {https://arxiv.org/abs/1908.10084},
  year = {2019},
}

@article{thakur2020augmented,
  title={Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks},
  author={Thakur, Nandan and Reimers, Nils and Daxenberger, Johannes and Gurevych, Iryna},
  journal={arXiv e-prints},
  pages={arXiv--2010},
  year={2020}
}

`Lajavaness/bilingual-embedding-small`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2024-07-17	eng-Latn, fra-Latn

Citation

@inproceedings{DBLP:journals/corr/abs-1911-02116,
  address = {Online},
  author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
  booktitle = {Proceedings of the 58th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics},
  doi = {10.18653/v1/2020.acl-main.747},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel},
  month = {jul},
  pages = {8440--8451},
  publisher = {Association for Computational Linguistics},
  title = {Unsupervised Cross-lingual Representation Learning at Scale},
  url = {https://aclanthology.org/2020.acl-main.747/},
  year = {2020},
}

@inproceedings{reimers-2019-sentence-bert,
  author = {Reimers, Nils and Gurevych, Iryna},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing},
  month = {11},
  publisher = {Association for Computational Linguistics},
  title = {Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
  url = {https://arxiv.org/abs/1908.10084},
  year = {2019},
}

@article{thakur2020augmented,
  title={Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks},
  author={Thakur, Nandan and Reimers, Nils and Daxenberger, Johannes and Gurevych, Iryna},
  journal={arXiv e-prints},
  pages={arXiv--2010},
  year={2020}
}

`Linkup-Platform/linkup-sparseup-embed-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
188.4M	50370	512	719.0 MB	2026-09-16	eng-Latn

`LiquidAI/LFM2-ColBERT-350M`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
353.3M	not specified	512	1.3 GB	2025-10-28	ara-Arab, deu-Latn, eng-Latn, fra-Latn, jpn-Jpan, ... (8)

Citation

@article{liquidai2025lfm2,
  title={LFM2 Technical Report},
  author={Liquid AI},
  journal={arXiv preprint arXiv:2511.23404},
  year={2025}
}

`LiquidAI/LFM2.5-ColBERT-350M`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
353.3M	not specified	512	674.0 MB	2026-06-18	ara-Arab, deu-Latn, eng-Latn, fra-Latn, ita-Latn, ... (11)

`MCINext/Hakim`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	512	475.0 MB	2025-05-10	fas-Arab

Citation

@article{sarmadi2025hakim,
      title={Hakim: Farsi Text Embedding Model},
      author={Sarmadi, Mehran and Alikhani, Morteza and Zinvandi, Erfan and Pourbahman, Zahra},
      journal={arXiv preprint arXiv:2505.08435},
      year={2025}
}

`MCINext/Hakim-small`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
38.7M	512	512	148.0 MB	2025-05-10	fas-Arab

Citation

@article{sarmadi2025hakim,
      title={Hakim: Farsi Text Embedding Model},
      author={Sarmadi, Mehran and Alikhani, Morteza and Zinvandi, Erfan and Pourbahman, Zahra},
      journal={arXiv preprint arXiv:2505.08435},
      year={2025}
}

`MCINext/Hakim-unsup`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	512	475.0 MB	2025-05-10	fas-Arab

Citation

@article{sarmadi2025hakim,
      title={Hakim: Farsi Text Embedding Model},
      author={Sarmadi, Mehran and Alikhani, Morteza and Zinvandi, Erfan and Pourbahman, Zahra},
      journal={arXiv preprint arXiv:2505.08435},
      year={2025}
}

`Mihaiii/Bulbasaur`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
17.4M	384	512	66.0 MB	2024-04-27	not specified

`Mihaiii/Ivysaur`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2024-04-27	not specified

`Mihaiii/Squirtle`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	384	512	60.0 MB	2024-04-30	not specified

`Mihaiii/Venusaur`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	384	512	60.0 MB	2024-04-29	not specified

`Mihaiii/Wartortle`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
17.4M	384	512	66.0 MB	2024-04-30	not specified

`Mihaiii/gte-micro`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
17.4M	384	512	66.0 MB	2024-04-21	not specified

`Mihaiii/gte-micro-v4`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
19.2M	384	512	73.0 MB	2024-04-22	not specified

`Mira190/Euler-Legal-Embedding-V1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6B	4096	1.5K	15.3 GB	2025-11-06	eng-Latn

`NGA-KR/ja-embed-sts`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
337.4M	1024	512	1.3 GB	2026-09-15	jpn-Jpan

`NGA-KR/ko-embed-cls`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	128	2.1 GB	2026-09-10	eng-Latn, kor-Hang

`NGA-KR/ko-embed-nli`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	128	2.1 GB	2026-09-10	eng-Latn, kor-Hang

`NbAiLab/nb-bert-base`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
177.9M	768	512	681.0 MB	2021-01-13	nno-Latn, nob-Latn

`NbAiLab/nb-bert-large`¶

License: cc-by-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
355.1M	1024	512	1.3 GB	2021-04-29	nno-Latn, nob-Latn

`NbAiLab/nb-sbert-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
177.9M	4096	75	678.0 MB	2022-11-23	dan-Latn, nno-Latn, nob-Latn, swe-Latn

`NeuML/pubmedbert-base-embeddings-100K`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
100.0K	64	Infinite	0.0 MB	2025-01-03	eng-Latn

`NeuML/pubmedbert-base-embeddings-1M`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.0M	64	Infinite	2.0 MB	2025-01-03	eng-Latn

`NeuML/pubmedbert-base-embeddings-2M`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.9M	64	Infinite	7.0 MB	2025-01-03	eng-Latn

`NeuML/pubmedbert-base-embeddings-500K`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
500.0K	64	Infinite	2.0 MB	2025-01-03	eng-Latn

`NeuML/pubmedbert-base-embeddings-8M`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.8M	256	Infinite	30.0 MB	2025-01-03	eng-Latn

`Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.2M	768	512	516.0 MB	2024-06-16	ara-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`Omartificial-Intelligence-Space/Arabic-MiniLM-L12-v2-all-nli-triplet`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2024-06-25	ara-Arab

`Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.2M	768	768	516.0 MB	2024-07-28	ara-Arab

Citation

    @article{nacar2025gate,
    title={GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training},
    author={Nacar, Omer and Koubaa, Anis and Sibaee, Serry and Al-Habashi, Yasser and Ammar, Adel and Boulila, Wadii},
    journal={arXiv preprint arXiv:2505.24581},
    year={2025}
}

`Omartificial-Intelligence-Space/Arabic-all-nli-triplet-Matryoshka`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2024-06-14	ara-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`Omartificial-Intelligence-Space/Arabic-labse-Matryoshka`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
470.9M	768	512	1.8 GB	2024-06-16	ara-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`Omartificial-Intelligence-Space/Arabic-mpnet-base-all-nli-triplet`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	514	418.0 MB	2024-06-15	ara-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`Omartificial-Intelligence-Space/Marbert-all-nli-triplet-Matryoshka`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
162.8M	768	512	621.0 MB	2024-06-17	ara-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`OpenSearch-AI/Ops-MoA-Conan-embedding-v1`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
343.4M	1536	512	1.3 GB	2025-03-26	zho-Hans

`OpenSearch-AI/Ops-MoA-Yuan-embedding-1.0`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
343.4M	1536	512	1.2 GB	2025-03-26	zho-Hans

`OrdalieTech/Solon-embeddings-large-0.1`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	514	2.1 GB	2023-12-09	fra-Latn

`OrdalieTech/Solon-embeddings-mini-beta-1.1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
211.8M	768	8.2K	808.0 MB	2025-01-01	fra-Latn

`PORTULAN/serafim-100m-portuguese-pt-sentence-encoder`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
108.9M	768	512	416.0 MB	2024-07-04	por-Latn

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PORTULAN/serafim-100m-portuguese-pt-sentence-encoder-ir`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
108.9M	768	512	416.0 MB	2024-07-04	not specified

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PORTULAN/serafim-335m-portuguese-pt-sentence-encoder`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
334.4M	1024	512	1.2 GB	2024-07-04	por-Latn

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
334.4M	1024	512	1.2 GB	2024-07-04	por-Latn

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PORTULAN/serafim-900m-portuguese-pt-sentence-encoder`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
884.6M	1536	512	3.3 GB	2024-07-04	por-Latn

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PORTULAN/serafim-900m-portuguese-pt-sentence-encoder-ir`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
884.6M	1536	512	3.3 GB	2024-07-04	por-Latn

Citation

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family},
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

`PartAI/Tooka-SBERT`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
353.0M	1024	512	1.3 GB	2024-12-07	fas-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`PartAI/Tooka-SBERT-V2-Large`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
353.0M	1024	512	1.3 GB	2025-05-01	fas-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`PartAI/Tooka-SBERT-V2-Small`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
122.9M	768	512	496.0 MB	2025-05-01	fas-Arab

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`PartAI/TookaBERT-Base`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
122.9M	768	512	469.0 MB	2024-12-08	fas-Arab

`Qodo/Qodo-Embed-1-1.5B`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	1536	32.8K	6.6 GB	2025-02-19	c#-Code, c++-Code, go-Code, java-Code, javascript-Code, ... (9)

`Qodo/Qodo-Embed-1-7B`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	3584	32.8K	28.4 GB	2025-02-24	c#-Code, c++-Code, go-Code, java-Code, javascript-Code, ... (9)

`Quazim0t0/Byrne-Embed`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
98.0M	768	128	327.0 MB	2026-06-20	eng-Latn

`Querit/Querit`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.9B	1024	4.1K	9.2 GB	2026-05-14	eng-Latn

Citation

@misc{zhong2026queritrerankertrainingcompactmultilingual,
      title={Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation},
      author={Yunfei Zhong and Jun Yang and Wei Huang and Yinqiong Cai and Haosheng Qian and Yixing Fan and Ruqing Zhang and Lixin Su and Daiting Shi and Jiafeng Guo},
      year={2026},
      eprint={2606.19037},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2606.19037},
}

`Querit/Querit-4B`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2026-06-14	eng-Latn

Citation

@misc{zhong2026queritrerankertrainingcompactmultilingual,
      title={Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation},
      author={Yunfei Zhong and Jun Yang and Wei Huang and Yinqiong Cai and Haosheng Qian and Yixing Fan and Ruqing Zhang and Lixin Su and Daiting Shi and Jiafeng Guo},
      year={2026},
      eprint={2606.19037},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2606.19037},
}

`RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-bilingual-ja-en`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
49.6M	512	Infinite	25.0 MB	2026-03-04	eng-Latn, jpn-Jpan

`RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-en`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	512	Infinite	8.0 MB	2026-02-21	eng-Latn

`RikkaBotan/quantized-stable-static-embedding-fast-retrieval-mrl-ja`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.8M	512	Infinite	9.0 MB	2026-02-28	jpn-Jpan

`RikkaBotan/stable-static-embedding-fast-retrieval-mrl-bilingual-ja-en`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
49.6M	512	Infinite	189.0 MB	2026-02-27	eng-Latn, jpn-Jpan

`RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	512	Infinite	60.0 MB	2026-02-08	eng-Latn

`RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en-v2`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	512	Infinite	60.0 MB	2026-05-12	eng-Latn

`RikkaBotan/stable-static-embedding-fast-retrieval-mrl-ja`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.8M	512	Infinite	64.0 MB	2026-02-28	jpn-Jpan

`RiverRider/motherlode-code-small-en-v0.1`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2026-09-27	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (8)

`Shuu12121/CodeSearch-ModernBERT-Crow-Plus`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
151.7M	768	1.0K	607.0 MB	2025-04-21	eng-Latn

`Shuu12121/NightOwl-CodeEmbedding`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
150.8M	768	1.0K	575.0 MB	2026-06-08	eng-Latn

`Singaraj/morisien-embed`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	1.0 GB	2026-08-09	eng-Latn, fra-Latn, mfe-Latn

`Singaraj/morisien-embed-v1.5`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
471.5M	768	256	1.8 GB	2026-09-06	eng-Latn, fra-Latn, mfe-Latn

`TencentBAC/Conan-embedding-v1`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	768	512	1.2 GB	2024-08-22	zho-Hans

Citation

@misc{li2024conanembeddinggeneraltextembedding,
  title={Conan-embedding: General Text Embedding with More and Better Negative Samples},
  author={Shiyu Li and Yang Tang and Shizhe Chen and Xi Chen},
  year={2024},
  eprint={2408.15710},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2408.15710},
}

`VAGOsolutions/SauerkrautLM-MoEdernColBERT-1.5M`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5M	128	32.8K	6.0 MB	2026-10-17	deu-Latn, eng-Latn, fra-Latn, ita-Latn, nld-Latn, ... (7)

`VAGOsolutions/SauerkrautLM-MoEdernColBERT-115M`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
114.6M	128	32.8K	437.0 MB	2026-10-17	deu-Latn, eng-Latn, fra-Latn, ita-Latn, nld-Latn, ... (7)

`VAGOsolutions/SauerkrautLM-MoEdernColBERT-27M`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
27.0M	128	32.8K	103.0 MB	2026-10-17	deu-Latn, eng-Latn, fra-Latn, ita-Latn, nld-Latn, ... (7)

`VoVanPhuc/sup-SimCSE-VietNamese-phobert-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.0M	768	256	517.0 MB	2021-05-26	vie-Latn

Citation

@inproceedings{gao2021simcse,
  address = {Online and Punta Cana, Dominican Republic},
  author = {Gao, Tianyu and Yao, Xingcheng and Chen, Danqi},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2021.emnlp-main.552},
  editor = {Moens, Marie-Francine and Huang, Xuanjing and Specia, Lucia and Yih, Scott Wen-tau},
  month = {nov},
  pages = {6894--6910},
  publisher = {Association for Computational Linguistics},
  title = {{S}im{CSE}: Simple Contrastive Learning of Sentence Embeddings},
  url = {https://aclanthology.org/2021.emnlp-main.552/},
  year = {2021},
}

@inproceedings{phobert,
title     = {{PhoBERT: Pre-trained language models for Vietnamese}},
author    = {Dat Quoc Nguyen and Anh Tuan Nguyen},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},
year      = {2020},
pages     = {1037--1042}
}

`aari1995/German_Semantic_STS_V2`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.7M	1024	512	1.3 GB	2022-11-17	deu-Latn

`abhinand/MedEmbed-small-v0.1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2024-10-20	eng-Latn

`ai-forever/sbert_large_mt_nlu_ru`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
427.0M	1024	512	1.6 GB	2021-05-18	rus-Cyrl

`ai-forever/sbert_large_nlu_ru`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
427.0M	1024	512	1.6 GB	2020-11-20	rus-Cyrl

`albertobarnabo/bge-m3-italian`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2026-09-13	ita-Latn

`alphabrothers/alpha-sts-v0`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	128	2.1 GB	2026-10-07	kor-Hang

`amazon/Titan-text-embeddings-v2`¶

License: custom • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2024-04-30	eng-Latn

`amgix/static-retrieval-multilingual-69m-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
69.1M	384	not specified	274.0 MB	2026-08-16	not specified

`andersborges/model2vecdk`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
48.0M	256	Infinite	183.0 MB	2025-11-21	dan-Latn

`andersborges/model2vecdk-stem`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
48.6M	256	Infinite	185.0 MB	2025-11-21	dan-Latn

`avsolatorio/GIST-Embedding-v0`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	418.0 MB	2024-01-31	eng-Latn

Citation

@article{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    journal={arXiv preprint arXiv:2402.16829},
    year={2024},
    URL={https://arxiv.org/abs/2402.16829}
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

`avsolatorio/GIST-all-MiniLM-L6-v2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2024-02-03	eng-Latn

Citation

@article{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    journal={arXiv preprint arXiv:2402.16829},
    year={2024},
    URL={https://arxiv.org/abs/2402.16829}
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

`avsolatorio/GIST-large-Embedding-v0`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	1.2 GB	2024-02-14	eng-Latn

Citation

@article{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    journal={arXiv preprint arXiv:2402.16829},
    year={2024},
    URL={https://arxiv.org/abs/2402.16829}
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

`avsolatorio/GIST-small-Embedding-v0`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2024-02-03	eng-Latn

Citation

@article{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    journal={arXiv preprint arXiv:2402.16829},
    year={2024},
    URL={https://arxiv.org/abs/2402.16829}
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

`avsolatorio/NoInstruct-small-Embedding-v0`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2024-05-01	eng-Latn

`axiotic/ogma-base`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
13.3M	256	1.0K	50.8 MB	2026-04-23	eng-Latn

`axiotic/ogma-micro`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.3M	128	1.0K	8.9 MB	2026-04-23	eng-Latn

`axiotic/ogma-mini`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.5M	256	1.0K	13.4 MB	2026-04-23	eng-Latn

`axiotic/ogma-small`¶

License: cc-by-nc-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.6M	256	1.0K	32.8 MB	2026-04-23	eng-Latn

`baseline/Human`¶

License: not specified • Openness: 2/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	not specified	ara-Arab, dan-Latn, eng-Latn, nob-Latn, rus-Cyrl

`bedrock/amazon-titan-embed-text-v1`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1536	8.2K	not specified	2023-09-27	not specified

`bedrock/amazon-titan-embed-text-v2`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	8.2K	not specified	2024-04-30	not specified

`bigscience/sgpt-bloom-7b1-msmarco`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	4096	not specified	not specified	2022-08-26	not specified

Citation

@article{muennighoff2022sgpt,
  title={SGPT: GPT Sentence Embeddings for Semantic Search},
  author={Muennighoff, Niklas},
  journal={arXiv preprint arXiv:2202.08904},
  year={2022}
}

`bisectgroup/BiCA-base`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	418.0 MB	2025-11-14	eng-Latn

Citation

@article{sinha2025bicaeffectivebiomedicaldense,
  author = {Sinha, Aarush and Kumar S, Pavan and Balaji, Roshan and Bhatt, Nirav Pravinbhai},
  doi = {10.1609/aaai.v40i39.40583},
  issn = {2159-5399},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  month = {Mar},
  number = {39},
  pages = {33010–33018},
  publisher = {Association for the Advancement of Artificial Intelligence (AAAI)},
  title = {BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives},
  url = {https://doi.org/10.1609/aaai.v40i39.40583},
  volume = {40},
  year = {2026},
}

`bkai-foundation-models/vietnamese-bi-encoder`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.0M	768	256	515.0 MB	2023-09-09	vie-Latn

Citation

      @article{duc2024towards,
    title={Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models},
    author={Nguyen Quang Duc, Le Hai Son, Nguyen Duc Nhan, Nguyen Dich Nhat Minh, Le Thanh Huong, Dinh Viet Sang},
    journal={arXiv preprint arXiv:2403.01616},
    year={2024}
  }

`brahmairesearch/slx-v0.1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2024-08-13	eng-Latn

`castorini/monot5-3b-msmarco-10k`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.0B	not specified	not specified	not specified	2022-03-28	eng-Latn

Citation

@misc{rosa2022parameterleftbehinddistillation,
      title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
      author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
      year={2022},
      eprint={2206.02873},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2206.02873},
    }

`castorini/monot5-base-msmarco-10k`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
296.9M	not specified	not specified	not specified	2022-03-28	eng-Latn

Citation

@misc{rosa2022parameterleftbehinddistillation,
      title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
      author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
      year={2022},
      eprint={2206.02873},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2206.02873},
    }

`castorini/monot5-large-msmarco-10k`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2022-03-28	eng-Latn

Citation

@misc{rosa2022parameterleftbehinddistillation,
      title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
      author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
      year={2022},
      eprint={2206.02873},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2206.02873},
    }

`castorini/monot5-small-msmarco-10k`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2022-03-28	eng-Latn

Citation

@misc{rosa2022parameterleftbehinddistillation,
      title={No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval},
      author={Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira},
      year={2022},
      eprint={2206.02873},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2206.02873},
    }

`cnmoro/static-nomic-384-pten-v2-st`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
106.1M	384	Infinite	405.0 MB	2026-08-04	eng-Latn, por-Latn

`codesage/codesage-base-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
354.7M	1024	2.0K	1.3 GB	2024-02-03	go-Code, java-Code, javascript-Code, php-Code, python-Code, ... (6)

Citation

@inproceedings{zhang2024code,
  archiveprefix = {arXiv},
  eprint = {2402.01935},
  title = {{CODE} {REPRESENTATION} {LEARNING} {AT} {SCALE}},
  author = {Dejiao Zhang and Wasi Uddin Ahmad and Ming Tan and Hantian Ding and Ramesh Nallapati and Dan Roth and Xiaofei Ma and Bing Xiang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=vfzRRjumpX},
}

`codesage/codesage-large-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	2048	2.0K	4.8 GB	2024-02-03	go-Code, java-Code, javascript-Code, php-Code, python-Code, ... (6)

Citation

@inproceedings{zhang2024code,
  archiveprefix = {arXiv},
  eprint = {2402.01935},
  title = {{CODE} {REPRESENTATION} {LEARNING} {AT} {SCALE}},
  author = {Dejiao Zhang and Wasi Uddin Ahmad and Ming Tan and Hantian Ding and Ramesh Nallapati and Dan Roth and Xiaofei Ma and Bing Xiang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=vfzRRjumpX},
}

`codesage/codesage-small-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
128.0M	1024	2.0K	496.0 MB	2024-02-03	go-Code, java-Code, javascript-Code, php-Code, python-Code, ... (6)

Citation

@inproceedings{zhang2024code,
  archiveprefix = {arXiv},
  eprint = {2402.01935},
  title = {{CODE} {REPRESENTATION} {LEARNING} {AT} {SCALE}},
  author = {Dejiao Zhang and Wasi Uddin Ahmad and Ming Tan and Hantian Ding and Ramesh Nallapati and Dan Roth and Xiaofei Ma and Bing Xiang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=vfzRRjumpX},
}

`cointegrated/LaBSE-en-ru`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
129.0M	768	512	492.0 MB	2021-06-10	rus-Cyrl

`cointegrated/rubert-tiny`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
11.9M	312	512	45.0 MB	2021-05-24	rus-Cyrl

`cointegrated/rubert-tiny2`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
29.4M	312	2.0K	112.0 MB	2021-10-28	rus-Cyrl

`colbert-ir/colbertv2.0`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	not specified	180	418.0 MB	2024-09-21	eng-Latn

`consciousAI/cai-lunaris-text-embeddings`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	not specified	2023-06-22	not specified

`consciousAI/cai-stellaris-text-embeddings`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	768	514	not specified	2023-06-23	not specified

`contextboxai/halong_embedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2024-07-06	vie-Latn

`cross-encoder/ettin-reranker-150m-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	not specified	8.0K	568.0 MB	2026-05-15	eng-Latn

`cross-encoder/ettin-reranker-17m-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.8M	not specified	8.0K	64.0 MB	2026-05-15	eng-Latn

`cross-encoder/ettin-reranker-1b-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.0B	not specified	8.0K	3.8 GB	2026-05-15	eng-Latn

`cross-encoder/ettin-reranker-32m-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
31.9M	not specified	8.0K	122.0 MB	2026-05-15	eng-Latn

`cross-encoder/ettin-reranker-400m-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
394.8M	not specified	8.0K	1.5 GB	2026-05-15	eng-Latn

`cross-encoder/ettin-reranker-68m-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
68.1M	not specified	8.0K	260.0 MB	2026-05-15	eng-Latn

`cross-encoder/ms-marco-MiniLM-L12-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	127.0 MB	2021-04-16	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`cross-encoder/ms-marco-MiniLM-L2-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
15.6M	384	512	60.0 MB	2021-04-16	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`cross-encoder/ms-marco-MiniLM-L4-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
19.2M	384	512	73.0 MB	2021-04-16	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`cross-encoder/ms-marco-MiniLM-L6-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2021-04-16	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`cross-encoder/ms-marco-TinyBERT-L2-v2`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.4M	128	512	17.0 MB	2021-04-16	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`deepfile/embedder-100p`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2023-07-24	not specified

`deepvk/USER-bge-m3`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
359.0M	1024	8.2K	1.3 GB	2024-07-05	rus-Cyrl

`deepvk/deberta-v1-base`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.0M	768	512	473.0 MB	2023-02-07	rus-Cyrl

`divakantpandey/code-embed`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
79.0M	1536	8.2K	301.0 MB	2026-10-18	eng-Latn, python-Code

`divakantpandey/code-embed-v2`¶

License: cc-by-nc-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
131.4M	1536	1.0K	480.0 MB	2026-10-21	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (7)

`dmedhi/PawanEmbd-68M`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
67.8M	768	512	260.0 MB	2025-12-08	eng-Latn

`dragonkue/BGE-m3-ko`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-09-17	eng-Latn, kor-Hang

`dunzhang/stella-large-zh-v3-1792d`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
327.4M	1792	512	not specified	2024-02-17	zho-Hans

`dunzhang/stella-mrl-large-zh-v3.5-1792d`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	1792	512	1.2 GB	2024-02-27	zho-Hans

`dwzhu/e5-base-4k`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
112.2M	not specified	4.1K	not specified	2024-03-28	eng-Latn

Citation

@inproceedings{zhu2024longembed,
  address = {Miami, Florida, USA},
  author = {Zhu, Dawei and Wang, Liang and Yang, Nan and Song, Yifan and Wu, Wenhao and Wei, Furu and Li, Sujian},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2024.emnlp-main.47},
  editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
  month = {nov},
  pages = {802--816},
  publisher = {Association for Computational Linguistics},
  title = {{L}ong{E}mbed: Extending Embedding Models for Long Context Retrieval},
  url = {https://aclanthology.org/2024.emnlp-main.47/},
  year = {2024},
}

`erikkaum/lattice-retrieval`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
31.3M	[32, 64, 128, 256, 512, 1024]	Infinite	119.0 MB	2026-08-06	eng-Latn

`facebook/SONAR`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	512	not specified	2021-05-21	ace-Arab, ace-Latn, acm-Arab, acq-Arab, aeb-Arab, ... (204)

Citation

@misc{Duquenne:2023:sonar_arxiv,
  author = {Paul-Ambroise Duquenne and Holger Schwenk and Benoit Sagot},
  title = {{SONAR:} Sentence-Level Multimodal and Language-Agnostic Representations},
  publisher = {arXiv},
  year = {2023},
  url = {https://arxiv.org/abs/2308.11466},
}

`facebook/contriever-msmarco`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	572.0 MB	2022-06-25	eng-Latn

Citation

    @article{izacard2021contriever,
  archiveprefix = {arXiv},
  author = {Gautier Izacard and Mathilde Caron and Lucas Hosseini and Sebastian Riedel and Piotr Bojanowski and Armand Joulin and Edouard Grave},
  eprint = {2112.09118},
  issn = {2835-8856},
  journal = {Transactions on Machine Learning Research},
  note = {},
  title = {Unsupervised Dense Information Retrieval with Contrastive Learning},
  url = {https://openreview.net/forum?id=jKN1pXi7b0},
  year = {2022},
}

`fangxq/XYZ-embedding`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
325.5M	768	512	1.2 GB	2024-09-13	zho-Hans

`geoffsee/auto-g-embed-st`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	256	87.0 MB	2026-02-08	eng-Latn

`google/flan-t5-base`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
247.6M	not specified	not specified	944.0 MB	2022-10-21	eng-Latn

Citation

@article{10.48550/arxiv.2210.11416,
  archiveprefix = {arXiv},
  author = {Hyung Won Chung and Le Hou and Shayne Longpre and Barret Zoph and Yi Tay and William Fedus and Yunxuan Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Alex Castro-Ros and Marie Pellat and Kevin Robinson and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Yu and Vincent Y. Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed H. Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei},
  eprint = {2210.11416},
  journal = {J. Mach. Learn. Res.},
  pages = {70:1-70:53},
  title = {Scaling Instruction-Finetuned Language Models},
  url = {https://jmlr.org/papers/v25/23-0870.html},
  volume = {25},
  year = {2024},
}

`google/flan-t5-large`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
783.2M	not specified	not specified	2.9 GB	2022-10-21	eng-Latn

Citation

@article{10.48550/arxiv.2210.11416,
  archiveprefix = {arXiv},
  author = {Hyung Won Chung and Le Hou and Shayne Longpre and Barret Zoph and Yi Tay and William Fedus and Yunxuan Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Alex Castro-Ros and Marie Pellat and Kevin Robinson and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Yu and Vincent Y. Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed H. Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei},
  eprint = {2210.11416},
  journal = {J. Mach. Learn. Res.},
  pages = {70:1-70:53},
  title = {Scaling Instruction-Finetuned Language Models},
  url = {https://jmlr.org/papers/v25/23-0870.html},
  volume = {25},
  year = {2024},
}

`google/flan-t5-xl`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	10.6 GB	2022-10-21	eng-Latn

Citation

@article{10.48550/arxiv.2210.11416,
  archiveprefix = {arXiv},
  author = {Hyung Won Chung and Le Hou and Shayne Longpre and Barret Zoph and Yi Tay and William Fedus and Yunxuan Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Alex Castro-Ros and Marie Pellat and Kevin Robinson and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Yu and Vincent Y. Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed H. Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei},
  eprint = {2210.11416},
  journal = {J. Mach. Learn. Res.},
  pages = {70:1-70:53},
  title = {Scaling Instruction-Finetuned Language Models},
  url = {https://jmlr.org/papers/v25/23-0870.html},
  volume = {25},
  year = {2024},
}

`google/flan-t5-xxl`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	42.0 GB	2022-10-21	eng-Latn

Citation

@article{10.48550/arxiv.2210.11416,
  archiveprefix = {arXiv},
  author = {Hyung Won Chung and Le Hou and Shayne Longpre and Barret Zoph and Yi Tay and William Fedus and Yunxuan Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Alex Castro-Ros and Marie Pellat and Kevin Robinson and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Yu and Vincent Y. Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed H. Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei},
  eprint = {2210.11416},
  journal = {J. Mach. Learn. Res.},
  pages = {70:1-70:53},
  title = {Scaling Instruction-Finetuned Language Models},
  url = {https://jmlr.org/papers/v25/23-0870.html},
  volume = {25},
  year = {2024},
}

`hotchpotch/bekko-embedding-v1-a25m`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
123.2M	[64, 128, 256, 384]	8.2K	470.0 MB	2026-07-28	afr-Latn, als-Latn, amh-Ethi, anp-Deva, arb-Arab, ... (110)

Citation

@misc{tateno2026bekko,
  title={Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders},
  author={Yuichi Tateno},
  year={2026},
  eprint={2607.25180},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2607.25180},
}

`hotchpotch/bekko-embedding-v1-a8m`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
106.0M	[64, 128, 256, 384]	8.2K	202.0 MB	2026-07-28	afr-Latn, als-Latn, amh-Ethi, anp-Deva, arb-Arab, ... (110)

Citation

@misc{tateno2026bekko,
  title={Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders},
  author={Yuichi Tateno},
  year={2026},
  eprint={2607.25180},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2607.25180},
}

`hotchpotch/bekko-static-embedding-v1`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
204.8M	[32, 64, 128, 256, 512, 1024]	32.8K	391.0 MB	2026-10-21	arb-Arab, ben-Beng, bul-Cyrl, cat-Latn, ces-Latn, ... (42)

Citation

@misc{tateno2026bekko,
  title={Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders},
  author={Yuichi Tateno},
  year={2026},
  eprint={2607.25180},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2607.25180},
}

`iampanda/zpoint_large_embedding_zh`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	1792	512	1.2 GB	2024-06-04	zho-Hans

`iara-project/BERTimbau-large-matryoshka-sts-pt`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
334.4M	[64, 128, 256, 512, 1024]	512	1.2 GB	2026-03-23	por-Latn

Citation

@inbook{okamura2026multilingualaveragesmtebptbenchmark,
  author = {Okamura, Lucas Hideki Takeuchi and Alcoforado, Alexandre and Costa, Anna Helena Reali},
  booktitle = {Intelligent Systems},
  doi = {10.1007/978-3-032-39892-5_33},
  isbn = {9783032398925},
  issn = {1611-3349},
  month = {Oct},
  pages = {501–516},
  publisher = {Springer Nature Switzerland},
  title = {Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders},
  url = {https://doi.org/10.1007/978-3-032-39892-5_33},
  year = {2026},
}

`iara-project/ModBERTBr-matryoshka-sts-pt`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.5M	[64, 128, 256, 512, 768]	512	517.0 MB	2026-04-01	por-Latn

Citation

@inbook{okamura2026multilingualaveragesmtebptbenchmark,
  author = {Okamura, Lucas Hideki Takeuchi and Alcoforado, Alexandre and Costa, Anna Helena Reali},
  booktitle = {Intelligent Systems},
  doi = {10.1007/978-3-032-39892-5_33},
  isbn = {9783032398925},
  issn = {1611-3349},
  month = {Oct},
  pages = {501–516},
  publisher = {Springer Nature Switzerland},
  title = {Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders},
  url = {https://doi.org/10.1007/978-3-032-39892-5_33},
  year = {2026},
}

`iara-project/e5-large-matryoshka-sts-pt`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	[64, 128, 256, 512, 1024]	514	2.1 GB	2026-03-23	por-Latn

Citation

@inbook{okamura2026multilingualaveragesmtebptbenchmark,
  author = {Okamura, Lucas Hideki Takeuchi and Alcoforado, Alexandre and Costa, Anna Helena Reali},
  booktitle = {Intelligent Systems},
  doi = {10.1007/978-3-032-39892-5_33},
  isbn = {9783032398925},
  issn = {1611-3349},
  month = {Oct},
  pages = {501–516},
  publisher = {Springer Nature Switzerland},
  title = {Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders},
  url = {https://doi.org/10.1007/978-3-032-39892-5_33},
  year = {2026},
}

`ibm-granite/granite-embedding-107m-multilingual`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
107.0M	384	512	204.0 MB	2024-12-18	ara-Latn, ces-Latn, deu-Latn, eng-Latn, fra-Latn, ... (13)

Citation

@article{awasthy2025graniteembedding,
  title={Granite Embedding Models},
  author={Awasthy, Parul and Trivedi, Aashka and Li, Yulong and Bornea, Mihaela and Cox, David and Daniels, Abraham and Franz, Martin and Goodhart, Gabe and Iyer, Bhavani and Kumar, Vishwajeet and Lastras, Luis and McCarley, Scott and Murthy, Rudra and P, Vignesh and Rosenthal, Sara and Roukos, Salim and Sen, Jaydeep and Sharma, Sukriti and Sil, Avirup and Soule, Kate and Sultan, Arafat and Florian, Radu},
  journal={arXiv preprint arXiv:2502.20204},
  year={2025}
}

`ibm-granite/granite-embedding-125m-english`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.6M	768	512	238.0 MB	2024-12-18	eng-Latn

Citation

@article{awasthy2025graniteembedding,
  title={Granite Embedding Models},
  author={Awasthy, Parul and Trivedi, Aashka and Li, Yulong and Bornea, Mihaela and Cox, David and Daniels, Abraham and Franz, Martin and Goodhart, Gabe and Iyer, Bhavani and Kumar, Vishwajeet and Lastras, Luis and McCarley, Scott and Murthy, Rudra and P, Vignesh and Rosenthal, Sara and Roukos, Salim and Sen, Jaydeep and Sharma, Sukriti and Sil, Avirup and Soule, Kate and Sultan, Arafat and Florian, Radu},
  journal={arXiv preprint arXiv:2502.20204},
  year={2025}
}

`ibm-granite/granite-embedding-278m-multilingual`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	530.0 MB	2024-12-18	ara-Latn, ces-Latn, deu-Latn, eng-Latn, fra-Latn, ... (13)

Citation

@article{awasthy2025graniteembedding,
  title={Granite Embedding Models},
  author={Awasthy, Parul and Trivedi, Aashka and Li, Yulong and Bornea, Mihaela and Cox, David and Daniels, Abraham and Franz, Martin and Goodhart, Gabe and Iyer, Bhavani and Kumar, Vishwajeet and Lastras, Luis and McCarley, Scott and Murthy, Rudra and P, Vignesh and Rosenthal, Sara and Roukos, Salim and Sen, Jaydeep and Sharma, Sukriti and Sil, Avirup and Soule, Kate and Sultan, Arafat and Florian, Radu},
  journal={arXiv preprint arXiv:2502.20204},
  year={2025}
}

`ibm-granite/granite-embedding-30m-english`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
30.3M	384	512	58.0 MB	2024-12-18	eng-Latn

Citation

@article{awasthy2025graniteembedding,
  title={Granite Embedding Models},
  author={Awasthy, Parul and Trivedi, Aashka and Li, Yulong and Bornea, Mihaela and Cox, David and Daniels, Abraham and Franz, Martin and Goodhart, Gabe and Iyer, Bhavani and Kumar, Vishwajeet and Lastras, Luis and McCarley, Scott and Murthy, Rudra and P, Vignesh and Rosenthal, Sara and Roukos, Salim and Sen, Jaydeep and Sharma, Sukriti and Sil, Avirup and Soule, Kate and Sultan, Arafat and Florian, Radu},
  journal={arXiv preprint arXiv:2502.20204},
  year={2025}
}

`ibm-granite/granite-embedding-311m-multilingual-r2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
311.7M	[128, 256, 384, 512, 768]	8.2K	594.0 MB	2026-04-29	ara-Arab, aze-Latn, ben-Beng, bul-Cyrl, cat-Latn, ... (52)

Citation

@article{awasthy2026graniteembeddingmultilingualr2,
      title={Granite Embedding Multilingual R2 Models},
      author={Parul Awasthy and Aashka Trivedi and Yushu Yang and Ken Barker and Yulong Li and Bhavani Iyer and Martin Franz and Juergen Bross and Meet Doshi and Vignesh P and Vishwajeet Kumar and Todd Ward and Abraham Daniels and Madison Lee and Luis Lastras and Jaydeep Sen and Radu Florian},
      year={2026},
      journal={arXiv preprint arXiv:2605.13521}
      url={https://arxiv.org/abs/2605.13521},
}

`ibm-granite/granite-embedding-97m-multilingual-r2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
97.4M	384	8.2K	186.0 MB	2026-04-29	ara-Arab, aze-Latn, ben-Beng, bul-Cyrl, cat-Latn, ... (52)

Citation

@article{awasthy2026graniteembeddingmultilingualr2,
      title={Granite Embedding Multilingual R2 Models},
      author={Parul Awasthy and Aashka Trivedi and Yushu Yang and Ken Barker and Yulong Li and Bhavani Iyer and Martin Franz and Juergen Bross and Meet Doshi and Vignesh P and Vishwajeet Kumar and Todd Ward and Abraham Daniels and Madison Lee and Luis Lastras and Jaydeep Sen and Radu Florian},
      year={2026},
      journal={arXiv preprint arXiv:2605.13521}
      url={https://arxiv.org/abs/2605.13521},
}

`ibm-granite/granite-embedding-english-r2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	284.0 MB	2025-08-15	eng-Latn

Citation

@article{awasthy2025graniteembeddingr2models,
      title={Granite Embedding R2 Models},
      author={Parul Awasthy and Aashka Trivedi and Yulong Li and Meet Doshi and Riyaz Bhat and Vignesh P and Vishwajeet Kumar and Yushu Yang and Bhavani Iyer and Abraham Daniels and Rudra Murthy and Ken Barker and Martin Franz and Madison Lee and Todd Ward and Salim Roukos and David Cox and Luis Lastras and Jaydeep Sen and Radu Florian},
      year={2025},
      journal={arXiv preprint arXiv:2508.21085},
      url={https://arxiv.org/abs/2508.21085},
}

`ibm-granite/granite-embedding-small-english-r2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
47.7M	384	8.2K	91.0 MB	2025-08-15	eng-Latn

Citation

@article{awasthy2025graniteembeddingr2models,
      title={Granite Embedding R2 Models},
      author={Parul Awasthy and Aashka Trivedi and Yulong Li and Meet Doshi and Riyaz Bhat and Vignesh P and Vishwajeet Kumar and Yushu Yang and Bhavani Iyer and Abraham Daniels and Rudra Murthy and Ken Barker and Martin Franz and Madison Lee and Todd Ward and Salim Roukos and David Cox and Luis Lastras and Jaydeep Sen and Radu Florian},
      year={2025},
      journal={arXiv preprint arXiv:2508.21085},
      url={https://arxiv.org/abs/2508.21085},
}

`infgrad/Prism-Qwen3.5-Reranker-0.8B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
752.4M	1024	10.0K	1.4 GB	2026-04-26	eng-Latn, zho-Hans

Citation

@misc{zhang2026prismreranker,
  title={Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval},
  author={Dun Zhang},
  year={2026},
  eprint={2604.23734},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2604.23734}
}

`infgrad/Prism-Qwen3.5-Reranker-2B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.9B	2048	10.0K	3.5 GB	2026-04-26	eng-Latn, zho-Hans

Citation

@misc{zhang2026prismreranker,
  title={Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval},
  author={Dun Zhang},
  year={2026},
  eprint={2604.23734},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2604.23734}
}

`infgrad/Prism-Qwen3.5-Reranker-4B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.2B	2560	10.0K	7.8 GB	2026-04-26	eng-Latn, zho-Hans

Citation

@misc{zhang2026prismreranker,
  title={Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval},
  author={Dun Zhang},
  year={2026},
  eprint={2604.23734},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2604.23734}
}

`infgrad/Prism-Qwen3.5-Reranker-9B`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
9.0B	4096	10.0K	16.7 GB	2026-04-26	eng-Latn, zho-Hans

Citation

@misc{zhang2026prismreranker,
  title={Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval},
  author={Dun Zhang},
  year={2026},
  eprint={2604.23734},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2604.23734}
}

`infgrad/stella-base-en-v2`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	not specified	512	not specified	2023-10-19	eng-Latn

`infgrad/stella-base-zh-v3-1792d`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
104.0M	1792	512	not specified	2024-02-17	zho-Hans

`izhx/udever-bloom-1b1`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.1B	not specified	not specified	not specified	2023-10-24	aka-Latn, ara-Arab, asm-Beng, bam-Latn, ben-Beng, ... (45)

Citation

@inproceedings{zhang2023language,
  address = {Vienna, Austria},
  author = {Zhang, Xin and Li, Zehan and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Zhang, Min},
  booktitle = {Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling ({XLLM} 2025)},
  doi = {10.18653/v1/2025.xllm-1.21},
  editor = {Fei, Hao and Tu, Kewei and Zhang, Yuhui and Hu, Xiang and Han, Wenjuan and Jia, Zixia and Zheng, Zilong and Cao, Yixin and Zhang, Meishan and Lu, Wei and Siddharth, N. and {\O}vrelid, Lilja and Xue, Nianwen and Zhang, Yue},
  isbn = {979-8-89176-286-2},
  month = {aug},
  pages = {252--265},
  publisher = {Association for Computational Linguistics},
  title = {Language Models are Universal Embedders},
  url = {https://aclanthology.org/2025.xllm-1.21/},
  year = {2025},
}

`izhx/udever-bloom-3b`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.0B	not specified	not specified	not specified	2023-10-24	aka-Latn, ara-Arab, asm-Beng, bam-Latn, ben-Beng, ... (45)

Citation

@inproceedings{zhang2023language,
  address = {Vienna, Austria},
  author = {Zhang, Xin and Li, Zehan and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Zhang, Min},
  booktitle = {Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling ({XLLM} 2025)},
  doi = {10.18653/v1/2025.xllm-1.21},
  editor = {Fei, Hao and Tu, Kewei and Zhang, Yuhui and Hu, Xiang and Han, Wenjuan and Jia, Zixia and Zheng, Zilong and Cao, Yixin and Zhang, Meishan and Lu, Wei and Siddharth, N. and {\O}vrelid, Lilja and Xue, Nianwen and Zhang, Yue},
  isbn = {979-8-89176-286-2},
  month = {aug},
  pages = {252--265},
  publisher = {Association for Computational Linguistics},
  title = {Language Models are Universal Embedders},
  url = {https://aclanthology.org/2025.xllm-1.21/},
  year = {2025},
}

`izhx/udever-bloom-560m`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.2M	not specified	not specified	not specified	2023-10-24	aka-Latn, ara-Arab, asm-Beng, bam-Latn, ben-Beng, ... (45)

Citation

@inproceedings{zhang2023language,
  address = {Vienna, Austria},
  author = {Zhang, Xin and Li, Zehan and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Zhang, Min},
  booktitle = {Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling ({XLLM} 2025)},
  doi = {10.18653/v1/2025.xllm-1.21},
  editor = {Fei, Hao and Tu, Kewei and Zhang, Yuhui and Hu, Xiang and Han, Wenjuan and Jia, Zixia and Zheng, Zilong and Cao, Yixin and Zhang, Meishan and Lu, Wei and Siddharth, N. and {\O}vrelid, Lilja and Xue, Nianwen and Zhang, Yue},
  isbn = {979-8-89176-286-2},
  month = {aug},
  pages = {252--265},
  publisher = {Association for Computational Linguistics},
  title = {Language Models are Universal Embedders},
  url = {https://aclanthology.org/2025.xllm-1.21/},
  year = {2025},
}

`izhx/udever-bloom-7b1`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2023-10-24	aka-Latn, ara-Arab, asm-Beng, bam-Latn, ben-Beng, ... (45)

Citation

@inproceedings{zhang2023language,
  address = {Vienna, Austria},
  author = {Zhang, Xin and Li, Zehan and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Zhang, Min},
  booktitle = {Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling ({XLLM} 2025)},
  doi = {10.18653/v1/2025.xllm-1.21},
  editor = {Fei, Hao and Tu, Kewei and Zhang, Yuhui and Hu, Xiang and Han, Wenjuan and Jia, Zixia and Zheng, Zilong and Cao, Yixin and Zhang, Meishan and Lu, Wei and Siddharth, N. and {\O}vrelid, Lilja and Xue, Nianwen and Zhang, Yue},
  isbn = {979-8-89176-286-2},
  month = {aug},
  pages = {252--265},
  publisher = {Association for Computational Linguistics},
  title = {Language Models are Universal Embedders},
  url = {https://aclanthology.org/2025.xllm-1.21/},
  year = {2025},
}

`jhgan/ko-sroberta-multitask`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
110.6M	768	512	422.0 MB	2022-03-02	kor-Hang

`jhu-clsp/FollowIR-7B`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.1B	not specified	not specified	13.5 GB	2024-04-29	eng-Latn

Citation

    @inproceedings{weller2024followir,
  address = {Albuquerque, New Mexico},
  author = {Weller, Orion and Chang, Benjamin and MacAvaney, Sean and Lo, Kyle and Cohan, Arman and Van Durme, Benjamin and Lawrie, Dawn and Soldaini, Luca},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the {A}mericas Chapter of the {A}ssociation for {C}omputational {L}inguistics: Human Language Technologies (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.naacl-long.597},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  isbn = {979-8-89176-189-6},
  month = {apr},
  pages = {11926--11942},
  publisher = {Association for Computational Linguistics},
  title = {{F}ollow{IR}: Evaluating and Teaching Information Retrieval Models to Follow Instructions},
  url = {https://aclanthology.org/2025.naacl-long.597/},
  year = {2025},
}

`jinaai/jina-colbert-v2`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.4M	not specified	8.2K	1.0 GB	2024-08-16	ara-Arab, ben-Beng, deu-Latn, eng-Latn, fas-Arab, ... (22)

Citation

@inproceedings{xiao-etal-2024-jina,
    title = "{J}ina-{C}ol{BERT}-v2: A General-Purpose Multilingual Late Interaction Retriever",
    author = {Jha, Rohan  and
      Wang, Bo  and
      G{"u}nther, Michael  and
      Mastrapas, Georgios  and
      Sturua, Saba  and
      Mohr, Isabelle  and
      Koukounas, Andreas  and
      Wang, Mohammad Kalim  and
      Wang, Nan  and
      Xiao, Han},
    editor = {S{"a}lev{"a}, Jonne  and
      Owodunni, Abraham},
    booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.mrl-1.11/",
    doi = "10.18653/v1/2024.mrl-1.11",
    pages = "159--166",
    abstract = "Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT`s late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this paper, we introduce a novel architecture and a training framework to support long context window and multilingual retrieval. Leveraging Matryoshka Representation Loss, we further demonstrate that the reducing the embedding dimensionality from 128 to 64 has insignificant impact on the model`s retrieval performance and cut storage requirements by up to 50{\%}. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks,"
}

`jinaai/jina-embedding-b-en-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.6M	768	512	420.0 MB	2023-07-07	eng-Latn

Citation

@misc{günther2023jina,
      title={Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models},
      author={Michael Günther and Louis Milliken and Jonathan Geuter and Georgios Mastrapas and Bo Wang and Han Xiao},
      year={2023},
      eprint={2307.11224},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`jinaai/jina-embedding-s-en-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
35.3M	512	512	134.0 MB	2023-07-07	eng-Latn

Citation

@misc{günther2023jina,
      title={Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models},
      author={Michael Günther and Louis Milliken and Jonathan Geuter and Georgios Mastrapas and Bo Wang and Han Xiao},
      year={2023},
      eprint={2307.11224},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`jinaai/jina-embeddings-v2-base-en`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
137.4M	768	8.2K	262.0 MB	2023-09-27	eng-Latn

Citation

@misc{günther2023jina,
      title={Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents},
      author={Michael Günther and Jackmin Ong and Isabelle Mohr and Alaeddine Abdessalem and Tanguy Abel and Mohammad Kalim Akram and Susana Guzman and Georgios Mastrapas and Saba Sturua and Bo Wang and Maximilian Werk and Nan Wang and Han Xiao},
      year={2023},
      eprint={2310.19923},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`jinaai/jina-embeddings-v2-small-en`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
32.7M	512	8.2K	62.0 MB	2023-09-27	eng-Latn

Citation

@misc{günther2023jina,
      title={Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents},
      author={Michael Günther and Jackmin Ong and Isabelle Mohr and Alaeddine Abdessalem and Tanguy Abel and Mohammad Kalim Akram and Susana Guzman and Georgios Mastrapas and Saba Sturua and Bo Wang and Maximilian Werk and Nan Wang and Han Xiao},
      year={2023},
      eprint={2310.19923},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

`jinaai/jina-reranker-v2-base-multilingual`¶

License: not specified • Openness: 2/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	531.0 MB	2024-09-26	eng-Latn

`jinaai/jina-reranker-v3`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.8M	not specified	131.1K	1.1 GB	2025-09-18	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{wang2025jinarerankerv3lateinteractionlistwise,
      title={jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking},
      author={Feng Wang and Yuqing Li and Han Xiao},
      year={2025},
      eprint={2509.25085},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.25085},}

`jinaai/jina-reranker-v3.5`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.8M	not specified	131.1K	1.1 GB	2026-07-20	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{nasika2026jinarerankerv35,
      title={jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation},
      author={Christina Nasika and Feng Wang and Antonis Krasakis and Han Xiao},
      year={2026},
      eprint={2607.18152},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2607.18152},
}

`judicialmind/greenleaf-law-embed-tiny`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	1024	32.8K	1.1 GB	2026-08-22	ara-Arab, bul-Cyrl, ces-Latn, dan-Latn, deu-Latn, ... (36)

`keeeeenw/MicroLlama-text-embedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
271.9M	1024	2.0K	1.0 GB	2024-11-10	eng-Latn

`lakinekaki/all-MiniLM-L6-v2-genbais`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2026-03-01	eng-Latn

`lier007/xiaobu-embedding`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	1024	512	1.2 GB	2024-01-09	zho-Hans

`lier007/xiaobu-embedding-v2`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	768	512	1.2 GB	2024-06-30	zho-Hans

`lightonai/ColBERT-Zero`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-02-19	eng-Latn

Citation

@misc{chaffin2026colbertzeropretrainpretraincolbert,
  title         = {ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models},
  author        = {Antoine Chaffin and Luca Arnaboldi and Amélie Chatelain and Florent Krzakala},
  year          = {2026},
  eprint        = {2602.16609},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2602.16609},
}

`lightonai/ColBERT-Zero-supervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-02-19	eng-Latn

Citation

@misc{chaffin2026colbertzeropretrainpretraincolbert,
  title         = {ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models},
  author        = {Antoine Chaffin and Luca Arnaboldi and Amélie Chatelain and Florent Krzakala},
  year          = {2026},
  eprint        = {2602.16609},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2602.16609},
}

`lightonai/ColBERT-Zero-unsupervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-02-19	eng-Latn

Citation

@misc{chaffin2026colbertzeropretrainpretraincolbert,
  title         = {ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models},
  author        = {Antoine Chaffin and Luca Arnaboldi and Amélie Chatelain and Florent Krzakala},
  year          = {2026},
  eprint        = {2602.16609},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2602.16609},
}

`lightonai/DenseOn`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	568.0 MB	2026-04-21	eng-Latn

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/DenseOn-unsupervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	768	8.2K	568.0 MB	2026-04-21	eng-Latn

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/GTE-ModernColBERT-v1`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2025-04-30	eng-Latn

`lightonai/LateOn`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-04-21	eng-Latn

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/LateOn-Code`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-02-12	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (7)

`lightonai/LateOn-Code-edge`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.8M	48	8.0K	64.0 MB	2026-02-12	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (7)

`lightonai/LateOn-Code-edge-pretrain`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.8M	48	8.0K	64.0 MB	2026-02-12	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (7)

`lightonai/LateOn-Code-pretrain`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-02-12	eng-Latn, go-Code, java-Code, javascript-Code, php-Code, ... (7)

`lightonai/LateOn-unsupervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-04-21	eng-Latn

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/Reason-ModernColBERT`¶

License: cc-by-nc-4.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2025-05-22	eng-Latn

`lightonai/SlideOn`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
174.2M	32768	8.2K	381.0 MB	not specified	eng-Latn

`lightonai/mDenseOn`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	768	8.2K	1.1 GB	2026-07-30	ara-Arab, deu-Latn, eng-Latn, fra-Latn, go-Code, ... (15)

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/mDenseOn-unsupervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	768	8.2K	1.1 GB	2026-07-30	ara-Arab, deu-Latn, eng-Latn, fra-Latn, ita-Latn, ... (9)

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/mLateOn`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	128	8.2K	1.1 GB	2026-07-30	ara-Arab, deu-Latn, eng-Latn, fra-Latn, go-Code, ... (15)

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/mLateOn-unsupervised`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	128	8.2K	585.0 MB	2026-07-30	ara-Arab, deu-Latn, eng-Latn, fra-Latn, ita-Latn, ... (9)

Citation

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}

`lightonai/mSlideOn`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
339.4M	32768	8.2K	701.0 MB	not specified	ara-Arab, deu-Latn, eng-Latn, fra-Latn, go-Code, ... (15)

`llm-semantic-router/elephant-embeddings-v1-text-small`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	[768, 512, 256, 128, 64]	32.8K	585.0 MB	2025-04-16	afr-Latn, amh-Ethi, ast-Latn, azj-Latn, azj-Latn, ... (29)

`llm-semantic-router/mmbert-embed-32k-2d-matryoshka`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
306.9M	[64, 128, 256, 512, 768]	32.8K	585.0 MB	2026-01-26	afr-Latn, amh-Ethi, ast-Latn, azj-Latn, azj-Latn, ... (29)

`llmrails/ember-v1`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.0M	1024	512	1.2 GB	2023-10-10	eng-Latn

`m3hrdadfi/bert-zwnj-wnli-mean-tokens`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.3M	768	512	451.0 MB	2021-06-28	fas-Arab

`m3hrdadfi/roberta-zwnj-wnli-mean-tokens`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
118.3M	768	514	451.0 MB	2021-06-28	fas-Arab

`malenia1/ternary-weight-embedding`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
98.7M	1024	512	158.0 MB	2024-10-23	not specified

`manu/bge-m3-custom-fr`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-04-11	not specified

`manu/sentence_croissant_alpha_v0.2`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	2048	2.0K	2.4 GB	2024-03-15	not specified

`manu/sentence_croissant_alpha_v0.3`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	2048	2.0K	2.4 GB	2024-04-26	not specified

`manu/sentence_croissant_alpha_v0.4`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.3B	2048	2.0K	2.4 GB	2024-04-27	eng-Latn, fra-Latn

`meta-llama/Llama-2-7b-chat-hf`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.0B	not specified	not specified	not specified	2023-07-18	eng-Latn

Citation

@misc{touvron2023llama2openfoundation,
      title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
      author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
      year={2023},
      eprint={2307.09288},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2307.09288},
    }

`meta-llama/Llama-2-7b-hf`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2023-07-18	eng-Latn

Citation

@misc{touvron2023llama2openfoundation,
      title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
      author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
      year={2023},
      eprint={2307.09288},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2307.09288},
    }

`microsoft/speecht5_tts`¶

License: mit • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
146.3M	768	not specified	558.0 MB	2022-05-16	eng-Latn

Citation

@inproceedings{ao2022speecht5unifiedmodalencoderdecoderpretraining,
  address = {Dublin, Ireland},
  author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
  booktitle = {Proceedings of the 60th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2022.acl-long.393},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {5723--5738},
  publisher = {Association for Computational Linguistics},
  title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
  url = {https://aclanthology.org/2022.acl-long.393/},
  year = {2022},
}

`minetta/nemotron-3-embed-8b-legal`¶

License: openmdw-1.1 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.0B	4096	32.8K	14.8 GB	2026-07-25	eng-Latn

`minishlab/M2V_base_glove`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.0M	256	Infinite	391.0 MB	2024-09-21	eng-Latn

`minishlab/M2V_base_glove_subword`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
103.0M	256	Infinite	391.0 MB	2024-09-21	eng-Latn

`minishlab/M2V_base_output`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6M	256	Infinite	29.0 MB	2024-09-21	eng-Latn

`minishlab/M2V_multilingual_output`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
128.0M	256	Infinite	489.0 MB	2024-09-21	eng-Latn

`minishlab/potion-base-2M`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.0M	64	Infinite	7.0 MB	2024-10-29	eng-Latn

`minishlab/potion-base-32M`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
32.3M	512	Infinite	123.0 MB	2025-01-22	eng-Latn

`minishlab/potion-base-4M`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
3.8M	128	Infinite	14.0 MB	2024-10-29	eng-Latn

`minishlab/potion-base-8M`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.6M	256	Infinite	29.0 MB	2024-10-29	eng-Latn

`minishlab/potion-code-16M-v2`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
16.2M	256	Infinite	62.0 MB	2026-07-08	eng-Latn

`minishlab/potion-multilingual-128M`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
128.0M	256	Infinite	489.0 MB	2025-05-23	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (101)

`minishlab/potion-retrieval-32M`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
32.3M	512	Infinite	123.0 MB	2025-01-23	eng-Latn

`mistralai/Mistral-7B-Instruct-v0.2`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
7.2B	not specified	not specified	not specified	2023-12-11	eng-Latn

Citation

@misc{jiang2023mistral7b,
      title={Mistral 7B},
      author={Albert Q. Jiang and Alexandre Sablayrolles and Arthur Mensch and Chris Bamford and Devendra Singh Chaplot and Diego de las Casas and Florian Bressand and Gianna Lengyel and Guillaume Lample and Lucile Saulnier and Lélio Renard Lavaud and Marie-Anne Lachaux and Pierre Stock and Teven Le Scao and Thibaut Lavril and Thomas Wang and Timothée Lacroix and William El Sayed},
      year={2023},
      eprint={2310.06825},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2310.06825},
    }

`mixedbread-ai/deepset-mxbai-embed-de-large-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
487.1M	1024	514	929.0 MB	2024-07-12	deu-Latn, eng-Latn

`mixedbread-ai/mxbai-edge-colbert-v0-17m`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
17.0M	not specified	8.0K	64.0 MB	2025-10-16	eng-Latn

Citation

@misc{takehi2025fantasticsmallretrieverstrain,
      title={Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report},
      author={Rikiya Takehi and Benjamin Clavié and Sean Lee and Aamir Shakir},
      year={2025},
      eprint={2510.14880},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2510.14880},
}

`mixedbread-ai/mxbai-edge-colbert-v0-32m`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
32.0M	not specified	511	122.0 MB	2025-10-16	eng-Latn

Citation

@misc{takehi2025fantasticsmallretrieverstrain,
      title={Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report},
      author={Rikiya Takehi and Benjamin Clavié and Sean Lee and Aamir Shakir},
      year={2025},
      eprint={2510.14880},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2510.14880},
}

`mixedbread-ai/mxbai-rerank-base-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
184.4M	not specified	512	352.0 MB	2024-02-29	eng-Latn

`mixedbread-ai/mxbai-rerank-base-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
494.0M	896	32.8K	1.8 GB	2025-03-03	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (106)

Citation

@inproceedings{li2026prorank,
    title = "{ProRank}: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking",
    author = "LI, Xianming  and
      Shakir, Aamir  and
      Huang, Rui  and
      Lipp, Julius  and
      Clavi{'e}, Benjamin  and
      Li, Jing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-acl.51/",
    pages = "1026--1037",
    ISBN = "979-8-89176-395-1"
}

`mixedbread-ai/mxbai-rerank-large-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
435.1M	not specified	512	830.0 MB	2024-02-29	eng-Latn

`mixedbread-ai/mxbai-rerank-large-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.5B	1536	32.8K	5.8 GB	2025-03-03	afr-Latn, amh-Ethi, ara-Arab, asm-Beng, aze-Latn, ... (106)

Citation

@inproceedings{li2026prorank,
    title = "{ProRank}: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking",
    author = "LI, Xianming  and
      Shakir, Aamir  and
      Huang, Rui  and
      Lipp, Julius  and
      Clavi{'e}, Benjamin  and
      Li, Jing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-acl.51/",
    pages = "1026--1037",
    ISBN = "979-8-89176-395-1"
}

`mixedbread-ai/mxbai-rerank-xsmall-v1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
70.8M	not specified	512	135.0 MB	2024-02-29	eng-Latn

`moka-ai/m3e-base`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.3M	768	512	390.0 MB	2023-06-06	eng-Latn, zho-Hans

`moka-ai/m3e-large`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
325.5M	768	512	not specified	2023-06-21	eng-Latn, zho-Hans

`moka-ai/m3e-small`¶

License: custom • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
24.0M	512	512	not specified	2023-06-02	eng-Latn, zho-Hans

`mteb/baseline-bb25`¶

License: not specified • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
0	not specified	not specified	not specified	2026-02-06	not specified

Citation

@software{jeong2026bayesianbm25,
  title={Bayesian BM25: A Probabilistic Framework for Hybrid Text and Vector Search},
  author={Jeong, Jaepil},
  year={2026},
  doi={10.5281/zenodo.18414941},
  url={https://doi.org/10.5281/zenodo.18414941},
}
@software{jeong2026neural,
  title={From Bayesian Inference to Neural Computation: The Analytical Emergence of Neural Network Structure from Probabilistic Relevance Estimation},
  author={Jeong, Jaepil},
  year={2026},
  doi={10.5281/zenodo.18512411},
  url={https://doi.org/10.5281/zenodo.18512411},
}

`mteb/baseline-bm25s`¶

License: not specified • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
0	not specified	not specified	not specified	2026-05-06	cmn-Hans, cmn-Hant, deu-Latn, eng-Latn, fra-Latn, ... (15)

Citation

@misc{bm25s,
      title={BM25S: Orders of magnitude faster lexical search via eager sparse scoring},
      author={Xing Han Lù},
      year={2024},
      eprint={2407.03618},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2407.03618},
}

`mteb/baseline-bm25s-subword`¶

License: not specified • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
0	not specified	not specified	not specified	2026-05-06	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@misc{bm25s,
      title={BM25S: Orders of magnitude faster lexical search via eager sparse scoring},
      author={Xing Han Lù},
      year={2024},
      eprint={2407.03618},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2407.03618},
}

`myrkur/sentence-transformer-parsbert-fa`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
162.8M	768	512	621.0 MB	2024-12-10	fas-Arab

`naver/splade-code-06B`¶

License: cc-by-nc-sa-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	151936	41.0K	1.1 GB	2026-02-24	go-Code, java-Code, javascript-Code, php-Code, python-Code, ... (6)

`naver/splade-code-8B`¶

License: cc-by-nc-sa-4.0 • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.4B	151936	41.0K	15.6 GB	2026-02-24	go-Code, java-Code, javascript-Code, php-Code, python-Code, ... (6)

`naver/splade-v3`¶

License: cc-by-nc-sa-4.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	30522	512	418.0 MB	2024-03-08	eng-Latn

Citation

@misc{lassance2024spladev3,
  title={SPLADE-v3: New baselines for SPLADE},
  author={Carlos Lassance and Hervé Déjean and Thibault Formal and Stéphane Clinchant},
  year={2024},
  eprint={2403.06789},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2403.06789},
}

`naver/splade_v2_distil`¶

License: cc-by-nc-sa-4.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
67.0M	30522	512	256.0 MB	2023-04-18	eng-Latn

Citation

@misc{formal2021spladev2,
  title={SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval},
  author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
  year={2021},
  eprint={2109.10086},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2109.10086},
}

`nlpai-lab/KURE-Reranker-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	not specified	8.2K	3.2 GB	2026-09-23	eng-Latn, kor-Hang

`nlpai-lab/KURE-Reranker-nano`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.3M	not specified	8.2K	570.0 MB	2026-09-09	eng-Latn, kor-Hang

`nlpai-lab/KURE-Sparse-base`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
592.6M	280524	8.2K	1.1 GB	2026-10-12	eng-Latn, kor-Hang

`nlpai-lab/KURE-Sparse-nano`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.4M	36282	8.2K	285.0 MB	2026-10-12	eng-Latn, kor-Hang

`nlpai-lab/KURE-v1`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-12-18	eng-Latn, kor-Hang

`nlpai-lab/KURE-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
153.6M	128	8.2K	586.0 MB	2026-08-17	eng-Latn, kor-Hang

`nvidia/Nemotron-3-Embed-1B-BF16`¶

License: openmdw-1.1 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.1B	2048	32.8K	2.1 GB	2026-07-16	ara-Arab, asm-Beng, ben-Beng, bul-Cyrl, dan-Latn, ... (34)

`nvidia/Nemotron-3-Embed-8B-BF16`¶

License: openmdw-1.1 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
8.0B	4096	32.8K	14.8 GB	2026-07-16	ara-Arab, asm-Beng, ben-Beng, bul-Cyrl, dan-Latn, ... (34)

`nvidia/llama-nemotron-rerank-1b-v2`¶

License: openmdw-1.1 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.2B	2048	4.1K	2.3 GB	2025-10-16	eng-Latn

`omarelshehy/arabic-english-sts-matryoshka`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	514	2.1 GB	2024-10-13	ara-Arab, eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`openai/text-embedding-3-large`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	3072	8.2K	not specified	2024-01-25	not specified

`openai/text-embedding-3-large (embed_dim=512)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	512	8.2K	not specified	2024-01-25	not specified

`openai/text-embedding-3-small`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1536	8.2K	not specified	2024-01-25	not specified

`openai/text-embedding-3-small (embed_dim=512)`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	512	8.2K	not specified	2024-01-25	not specified

`openai/text-embedding-ada-002`¶

License: not specified • Openness: 1/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1536	8.2K	not specified	2022-12-15	not specified

`openbmb/MiniCPM-Embedding`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
2.7B	2304	512	5.1 GB	2024-09-04	eng-Latn, zho-Hans

`opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
167.6M	105879	512	639.0 MB	2025-02-21	ara-Arab, ben-Beng, eng-Latn, fas-Arab, fin-Latn, ... (15)

`opensearch-project/opensearch-neural-sparse-encoding-v2-distill`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
67.0M	30522	512	256.0 MB	2024-07-17	eng-Latn

`panalexeu/xlm-roberta-ua-distilled`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	1.0 GB	2025-04-15	eng-Latn, ukr-Cyrl

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`perplexity-ai/pplx-embed-v1-0.6b`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
596.0M	1024	32.8K	2.2 GB	2026-02-11	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@inproceedings{eslami2026diffusionpretraineddensecontextualembeddings,
  address = {San Diego, California, USA},
  author = {Eslami, Sedigheh and Gaiduk, Maksim and Krimmel, Markus and Milliken, Louis Mark and Wang, Bo and Bykov, Denis},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)},
  doi = {10.18653/v1/2026.acl-industry.69},
  editor = {Li, Yunyao and Rehm, Georg and Tu, Mei},
  isbn = {979-8-89176-394-4},
  month = {jul},
  pages = {990--1004},
  publisher = {Association for Computational Linguistics},
  title = {Diffusion-Pretrained Dense and Contextual Embeddings},
  url = {https://aclanthology.org/2026.acl-industry.69/},
  year = {2026},
}

`perplexity-ai/pplx-embed-v1-4b`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	15.0 GB	2026-02-11	afr-Latn, ara-Arab, aze-Latn, bel-Cyrl, ben-Beng, ... (73)

Citation

@inproceedings{eslami2026diffusionpretraineddensecontextualembeddings,
  address = {San Diego, California, USA},
  author = {Eslami, Sedigheh and Gaiduk, Maksim and Krimmel, Markus and Milliken, Louis Mark and Wang, Bo and Bykov, Denis},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)},
  doi = {10.18653/v1/2026.acl-industry.69},
  editor = {Li, Yunyao and Rehm, Georg and Tu, Mei},
  isbn = {979-8-89176-394-4},
  month = {jul},
  pages = {990--1004},
  publisher = {Association for Computational Linguistics},
  title = {Diffusion-Pretrained Dense and Contextual Embeddings},
  url = {https://aclanthology.org/2026.acl-industry.69/},
  year = {2026},
}

`perplexity-ai/pplx-embed-v1-late-0.6b`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
595.8M	128	512	2.2 GB	2026-03-13	not specified

`prdev/mini-gte`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
66.4M	768	512	253.0 MB	2025-01-28	eng-Latn

`rasgaard/m2v-dfm-large`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.9M	256	Infinite	87.0 MB	2025-10-08	dan-Latn

`richinfoai/ritrieve_zh_v1`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
326.0M	1792	512	1.2 GB	2025-03-25	zho-Hans

`rufimelo/Legal-BERTimbau-sts-large-ma-v3`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
334.4M	1024	512	1.2 GB	2022-09-21	por-Latn

`sbintuitions/sarashina-embedding-v1-1b`¶

License: custom • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.2B	1792	8.2K	4.6 GB	2024-11-22	jpn-Jpan

`sbunlp/fabert`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	512	475.0 MB	2024-10-07	fas-Arab

Citation

@inproceedings{masumi-etal-2025-fabert,
    title = "{F}a{BERT}: Pre-training {BERT} on {P}ersian Blogs",
    author = "Masumi, Mostafa  and
      Majd, Seyed Soroush  and
      Shamsfard, Mehrnoush  and
      Beigy, Hamid",
    editor = "Bak, JinYeong  and
      Goot, Rob van der  and
      Jang, Hyeju  and
      Buaphet, Weerayut  and
      Ramponi, Alan  and
      Xu, Wei  and
      Ritter, Alan",
    booktitle = "Proceedings of the Tenth Workshop on Noisy and User-generated Text",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.wnut-1.10/",
    doi = "10.18653/v1/2025.wnut-1.10",
    pages = "85--96",
    ISBN = "979-8-89176-232-9",
}

`sdadas/mmlw-e5-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	514	1.0 GB	2023-11-17	pol-Latn

Citation

@inproceedings{dadas2024pirb,
  address = {Torino, Italia},
  archiveprefix = {arXiv},
  author = {Dadas, Slawomir and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC}-{COLING} 2024)},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  eprint = {2402.13350},
  month = {may},
  pages = {12761--12774},
  publisher = {ELRA and ICCL},
  title = {{PIRB}: A Comprehensive Benchmark of {P}olish Dense and Hybrid Text Retrieval Methods},
  url = {https://aclanthology.org/2024.lrec-main.1117/},
  year = {2024},
}

`sdadas/mmlw-e5-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
559.9M	1024	514	2.1 GB	2023-11-17	pol-Latn

Citation

@inproceedings{dadas2024pirb,
  address = {Torino, Italia},
  archiveprefix = {arXiv},
  author = {Dadas, Slawomir and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC}-{COLING} 2024)},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  eprint = {2402.13350},
  month = {may},
  pages = {12761--12774},
  publisher = {ELRA and ICCL},
  title = {{PIRB}: A Comprehensive Benchmark of {P}olish Dense and Hybrid Text Retrieval Methods},
  url = {https://aclanthology.org/2024.lrec-main.1117/},
  year = {2024},
}

`sdadas/mmlw-e5-small`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2023-11-17	pol-Latn

Citation

@inproceedings{dadas2024pirb,
  address = {Torino, Italia},
  archiveprefix = {arXiv},
  author = {Dadas, Slawomir and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC}-{COLING} 2024)},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  eprint = {2402.13350},
  month = {may},
  pages = {12761--12774},
  publisher = {ELRA and ICCL},
  title = {{PIRB}: A Comprehensive Benchmark of {P}olish Dense and Hybrid Text Retrieval Methods},
  url = {https://aclanthology.org/2024.lrec-main.1117/},
  year = {2024},
}

`sdadas/mmlw-roberta-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
124.4M	768	514	475.0 MB	2023-11-17	pol-Latn

Citation

@inproceedings{dadas2024pirb,
  address = {Torino, Italia},
  archiveprefix = {arXiv},
  author = {Dadas, Slawomir and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC}-{COLING} 2024)},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  eprint = {2402.13350},
  month = {may},
  pages = {12761--12774},
  publisher = {ELRA and ICCL},
  title = {{PIRB}: A Comprehensive Benchmark of {P}olish Dense and Hybrid Text Retrieval Methods},
  url = {https://aclanthology.org/2024.lrec-main.1117/},
  year = {2024},
}

`sdadas/mmlw-roberta-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
435.0M	1024	514	1.6 GB	2023-11-17	pol-Latn

Citation

@inproceedings{dadas2024pirb,
  address = {Torino, Italia},
  archiveprefix = {arXiv},
  author = {Dadas, Slawomir and Pere{\l}kiewicz, Micha{\l} and Po{\'s}wiata, Rafa{\l}},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC}-{COLING} 2024)},
  editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  eprint = {2402.13350},
  month = {may},
  pages = {12761--12774},
  publisher = {ELRA and ICCL},
  title = {{PIRB}: A Comprehensive Benchmark of {P}olish Dense and Hybrid Text Retrieval Methods},
  url = {https://aclanthology.org/2024.lrec-main.1117/},
  year = {2024},
}

`sensenova/piccolo-base-zh`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.3M	768	512	not specified	2023-09-04	zho-Hans

`sensenova/piccolo-large-zh-v2`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	1024	512	not specified	2024-04-22	zho-Hans

Citation

@misc{2405.06932,
    Author = {Junqin Huang and Zhongjie Hu and Zihao Jing and Mengya Gao and Yichao Wu},
    Title = {Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training},
    Year = {2024},
    Eprint = {arXiv:2405.06932},
}

`sentence-transformers/LaBSE`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
470.9M	768	512	1.8 GB	2019-11-01	ara-Arab, bul-Cyrl, cat-Latn, ces-Latn, dan-Latn, ... (53)

Citation

@inproceedings{feng2022languageagnosticbertsentenceembedding,
  address = {Dublin, Ireland},
  author = {Feng, Fangxiaoyu and Yang, Yinfei and Cer, Daniel and Arivazhagan, Naveen and Wang, Wei},
  booktitle = {Proceedings of the 60th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2022.acl-long.62},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {878--891},
  publisher = {Association for Computational Linguistics},
  title = {Language-agnostic {BERT} Sentence Embedding},
  url = {https://aclanthology.org/2022.acl-long.62/},
  year = {2022},
}

`sentence-transformers/all-MiniLM-L12-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	256	127.0 MB	2021-08-30	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/all-MiniLM-L6-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	256	87.0 MB	2021-08-30	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/all-mpnet-base-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	384	418.0 MB	2021-08-30	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/gtr-t5-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
110.2M	768	512	209.0 MB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021largedualencodersgeneralizable,
  address = {Abu Dhabi, United Arab Emirates},
  author = {Ni, Jianmo and Qu, Chen and Lu, Jing and Dai, Zhuyun and Hernandez Abrego, Gustavo and Ma, Ji and Zhao, Vincent and Luan, Yi and Hall, Keith and Chang, Ming-Wei and Yang, Yinfei},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2022.emnlp-main.669},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  month = {dec},
  pages = {9844--9855},
  publisher = {Association for Computational Linguistics},
  title = {Large Dual Encoders Are Generalizable Retrievers},
  url = {https://aclanthology.org/2022.emnlp-main.669/},
  year = {2022},
}

`sentence-transformers/gtr-t5-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.7M	768	512	639.0 MB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021largedualencodersgeneralizable,
  address = {Abu Dhabi, United Arab Emirates},
  author = {Ni, Jianmo and Qu, Chen and Lu, Jing and Dai, Zhuyun and Hernandez Abrego, Gustavo and Ma, Ji and Zhao, Vincent and Luan, Yi and Hall, Keith and Chang, Ming-Wei and Yang, Yinfei},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2022.emnlp-main.669},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  month = {dec},
  pages = {9844--9855},
  publisher = {Association for Computational Linguistics},
  title = {Large Dual Encoders Are Generalizable Retrievers},
  url = {https://aclanthology.org/2022.emnlp-main.669/},
  year = {2022},
}

`sentence-transformers/gtr-t5-xl`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.2B	768	512	2.3 GB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021largedualencodersgeneralizable,
  address = {Abu Dhabi, United Arab Emirates},
  author = {Ni, Jianmo and Qu, Chen and Lu, Jing and Dai, Zhuyun and Hernandez Abrego, Gustavo and Ma, Ji and Zhao, Vincent and Luan, Yi and Hall, Keith and Chang, Ming-Wei and Yang, Yinfei},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2022.emnlp-main.669},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  month = {dec},
  pages = {9844--9855},
  publisher = {Association for Computational Linguistics},
  title = {Large Dual Encoders Are Generalizable Retrievers},
  url = {https://aclanthology.org/2022.emnlp-main.669/},
  year = {2022},
}

`sentence-transformers/gtr-t5-xxl`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.9B	768	512	9.1 GB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021largedualencodersgeneralizable,
  address = {Abu Dhabi, United Arab Emirates},
  author = {Ni, Jianmo and Qu, Chen and Lu, Jing and Dai, Zhuyun and Hernandez Abrego, Gustavo and Ma, Ji and Zhao, Vincent and Luan, Yi and Hall, Keith and Chang, Ming-Wei and Yang, Yinfei},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2022.emnlp-main.669},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  month = {dec},
  pages = {9844--9855},
  publisher = {Association for Computational Linguistics},
  title = {Large Dual Encoders Are Generalizable Retrievers},
  url = {https://aclanthology.org/2022.emnlp-main.669/},
  year = {2022},
}

`sentence-transformers/multi-qa-MiniLM-L6-cos-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
22.7M	384	512	87.0 MB	2021-08-30	eng-Latn

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/multi-qa-mpnet-base-dot-v1`¶

License: not specified • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	418.0 MB	2021-08-23	eng-Latn

`sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	512	449.0 MB	2019-11-01	ara-Arab, bul-Cyrl, cat-Latn, ces-Latn, dan-Latn, ... (53)

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/paraphrase-multilingual-mpnet-base-v2`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
278.0M	768	512	1.0 GB	2019-11-01	ara-Arab, bul-Cyrl, cat-Latn, ces-Latn, dan-Latn, ... (53)

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

`sentence-transformers/sentence-t5-base`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
222.9M	768	512	209.0 MB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021sentencet5scalablesentenceencoders,
  address = {Dublin, Ireland},
  author = {Ni, Jianmo and Hernandez Abrego, Gustavo and Constant, Noah and Ma, Ji and Hall, Keith and Cer, Daniel and Yang, Yinfei},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2022},
  doi = {10.18653/v1/2022.findings-acl.146},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {1864--1874},
  publisher = {Association for Computational Linguistics},
  title = {{S}entence-{T}5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models},
  url = {https://aclanthology.org/2022.findings-acl.146/},
  year = {2022},
}

`sentence-transformers/sentence-t5-large`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.7M	768	512	639.0 MB	2022-02-09	eng-Latn

Citation

@inproceedings{ni2021sentencet5scalablesentenceencoders,
  address = {Dublin, Ireland},
  author = {Ni, Jianmo and Hernandez Abrego, Gustavo and Constant, Noah and Ma, Ji and Hall, Keith and Cer, Daniel and Yang, Yinfei},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2022},
  doi = {10.18653/v1/2022.findings-acl.146},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {1864--1874},
  publisher = {Association for Computational Linguistics},
  title = {{S}entence-{T}5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models},
  url = {https://aclanthology.org/2022.findings-acl.146/},
  year = {2022},
}

`sentence-transformers/sentence-t5-xl`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.2B	768	512	2.3 GB	2024-03-27	eng-Latn

Citation

@inproceedings{ni2021sentencet5scalablesentenceencoders,
  address = {Dublin, Ireland},
  author = {Ni, Jianmo and Hernandez Abrego, Gustavo and Constant, Noah and Ma, Ji and Hall, Keith and Cer, Daniel and Yang, Yinfei},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2022},
  doi = {10.18653/v1/2022.findings-acl.146},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {1864--1874},
  publisher = {Association for Computational Linguistics},
  title = {{S}entence-{T}5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models},
  url = {https://aclanthology.org/2022.findings-acl.146/},
  year = {2022},
}

`sentence-transformers/sentence-t5-xxl`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.9B	768	512	9.1 GB	2024-03-27	eng-Latn

Citation

@inproceedings{ni2021sentencet5scalablesentenceencoders,
  address = {Dublin, Ireland},
  author = {Ni, Jianmo and Hernandez Abrego, Gustavo and Constant, Noah and Ma, Ji and Hall, Keith and Cer, Daniel and Yang, Yinfei},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2022},
  doi = {10.18653/v1/2022.findings-acl.146},
  editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  month = {may},
  pages = {1864--1874},
  publisher = {Association for Computational Linguistics},
  title = {{S}entence-{T}5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models},
  url = {https://aclanthology.org/2022.findings-acl.146/},
  year = {2022},
}

`sentence-transformers/static-retrieval-mrl-en-v1`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
31.3M	1024	Infinite	119.0 MB	2024-10-24	eng-Latn

`sentence-transformers/static-similarity-mrl-multilingual-v1`¶

License: apache-2.0 • Openness: 6/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
108.4M	1024	not specified	413.0 MB	2025-01-15	ara-Arab, bul-Cyrl, cat-Latn, ces-Latn, dan-Latn, ... (49)

Citation

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

`sergeyzh/LaBSE-ru-turbo`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
129.0M	768	512	490.0 MB	2024-06-27	rus-Cyrl

`sergeyzh/rubert-tiny-turbo`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
29.2M	312	2.0K	111.0 MB	2024-06-21	rus-Cyrl

`shekar-ai/Noql`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
11.9M	[768, 512, 256, 128, 64]	512	46.0 MB	2026-09-22	fas-Arab

`shibing624/text2vec-base-chinese`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.3M	768	512	390.0 MB	2022-01-23	zho-Hans

`shibing624/text2vec-base-chinese-paraphrase`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.9M	768	512	450.0 MB	2023-06-19	zho-Hans

`shibing624/text2vec-base-multilingual`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
117.7M	384	256	449.0 MB	2023-06-22	deu-Latn, eng-Latn, fra-Latn, ita-Latn, nld-Latn, ... (10)

`silma-ai/silma-embeddding-matryoshka-v0.1`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
135.2M	768	512	516.0 MB	2024-10-12	ara-Arab, eng-Latn

`spartan8806/atles-champion-embedding`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	420.0 MB	2025-11-15	eng-Latn

`sshalimov04/ru-reranker-edge-150m`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	not specified	8.2K	570.0 MB	2026-09-06	rus-Cyrl

`stephantulkens/NIFE-gte-modernbert-base_as_router`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
225.8M	768	8.2K	861.0 MB	2025-10-30	eng-Latn

Citation

@software{Tulkens2025pyNIFE,
  author       = {St'{e}phan Tulkens},
  title        = {pyNIFE: nearly inference free embeddings in python},
  year         = {2025},
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.17512919},
  url          = {https://github.com/stephantul/pynife},
  license      = {MIT},
}

`stephantulkens/NIFE-mxbai-embed-large-v1_as_router`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
445.7M	1024	512	1.7 GB	2025-11-03	eng-Latn

Citation

@software{Tulkens2025pyNIFE,
  author       = {St'{e}phan Tulkens},
  title        = {pyNIFE: nearly inference free embeddings in python},
  year         = {2025},
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.17512919},
  url          = {https://github.com/stephantul/pynife},
  license      = {MIT},
}

`telepix/PIXIE-Splade-v1.5`¶

License: apache-2.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.4M	50000	5.6K	570.0 MB	2026-04-22	eng-Latn, kor-Hang

`thenlper/gte-base`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
109.5M	768	512	209.0 MB	2023-07-27	eng-Latn

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thenlper/gte-base-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
102.3M	1024	512	195.0 MB	2023-11-08	zho-Hans

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thenlper/gte-large`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	512	639.0 MB	2023-07-27	eng-Latn

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thenlper/gte-large-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
325.5M	1024	512	621.0 MB	2023-11-08	zho-Hans

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thenlper/gte-small`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	64.0 MB	2023-07-27	eng-Latn

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thenlper/gte-small-zh`¶

License: mit • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
30.3M	1024	512	58.0 MB	2023-11-08	zho-Hans

Citation

@article{li2023towards,
  title={Towards general text embeddings with multi-stage contrastive learning},
  author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
  journal={arXiv preprint arXiv:2308.03281},
  year={2023}
}

`thu-nmrc/bge-small-structural-separator`¶

License: mit • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
33.4M	384	512	not specified	2026-07-14	eng-Latn

`topk-io/Iso-ModernColBERT`¶

License: apache-2.0 • Openness: 4/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
149.0M	128	8.2K	568.0 MB	2026-05-27	eng-Latn

`unicamp-dl/mt5-base-mmarco-v2`¶

License: not specified • Openness: 3/6

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
not specified	not specified	not specified	not specified	2022-01-05	afr-Latn, amh-Ethi, ara-Arab, aze-Latn, bel-Cyrl, ... (103)

Citation

@article{DBLP:journals/corr/abs-2108-13897,
  author = {Luiz Bonifacio and
Israel Campiotti and
Roberto de Alencar Lotufo and
Rodrigo Frassetto Nogueira},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2108-13897.bib},
  eprint = {2108.13897},
  eprinttype = {arXiv},
  journal = {CoRR},
  timestamp = {Mon, 20 Mar 2023 15:35:34 +0100},
  title = {mMARCO: {A} Multilingual Version of {MS} {MARCO} Passage Ranking Dataset},
  url = {https://arxiv.org/abs/2108.13897},
  volume = {abs/2108.13897},
  year = {2021},
}

`upskyy/bge-m3-korean`¶

License: not specified • Openness: 2/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
567.8M	1024	8.2K	2.1 GB	2024-08-09	eng-Latn, kor-Hang

`w601sxs/b1ade-embed`¶

License: mit • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
335.1M	1024	4.1K	1.2 GB	2025-03-10	eng-Latn

`xpmir/Mice-P-130m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
128.6M	not specified	8.0K	490.0 MB	2026-10-15	eng-Latn

Citation

@misc{morand2026micemeetyoureranking,
  title={MICE to Meet You: From Re-ranking Only to End-to-End Retrieval},
  author={Victor Morand and Yuxuan Zong and Mathias Vast and Josiane Mothe and Benjamin Piwowarski},
  year={2026},
  eprint={2610.31932},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2610.31932}
}

`xpmir/Mice-P-61m`¶

License: apache-2.0 • Openness: 5/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
61.3M	not specified	8.0K	234.0 MB	2026-10-15	eng-Latn

Citation

@misc{morand2026micemeetyoureranking,
  title={MICE to Meet You: From Re-ranking Only to End-to-End Retrieval},
  author={Victor Morand and Yuxuan Zong and Mathias Vast and Josiane Mothe and Benjamin Piwowarski},
  year={2026},
  eprint={2610.31932},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2610.31932}
}

`zeroentropy/zembed-1`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	32.8K	7.5 GB	2026-03-02	ara-Arab, deu-Latn, eng-Latn, fin-Latn, fra-Latn, ... (15)

Citation

@misc{pipitone2025zeloeloinspiredtrainingmethod,
      title={zELO: ELO-inspired Training Method for Rerankers and Embedding Models},
      author={Nicholas Pipitone and Ghita Houir Alami and Advaith Avadhanam and Anton Kaminskyi and Ashley Khoo},
      year={2025},
      eprint={2509.12541},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.12541},
}

`zeroentropy/zerank-1`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2025-07-01	eng-Latn

Citation

@misc{pipitone2025zeloeloinspiredtrainingmethod,
      title={zELO: ELO-inspired Training Method for Rerankers and Embedding Models},
      author={Nicholas Pipitone and Ghita Houir Alami and Advaith Avadhanam and Anton Kaminskyi and Ashley Khoo},
      year={2025},
      eprint={2509.12541},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.12541},
}

`zeroentropy/zerank-1-small`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
1.7B	2048	41.0K	3.2 GB	2025-07-01	eng-Latn

Citation

@misc{pipitone2025zeloeloinspiredtrainingmethod,
      title={zELO: ELO-inspired Training Method for Rerankers and Embedding Models},
      author={Nicholas Pipitone and Ghita Houir Alami and Advaith Avadhanam and Anton Kaminskyi and Ashley Khoo},
      year={2025},
      eprint={2509.12541},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.12541},
}

`zeroentropy/zerank-2`¶

License: cc-by-nc-4.0 • Openness: 3/6 • Learn more →

Parameters	Emb. Dim	Max Tokens	Memory	Released	Languages
4.0B	2560	41.0K	7.5 GB	2025-11-19	eng-Latn

Citation

@misc{pipitone2025zeloeloinspiredtrainingmethod,
      title={zELO: ELO-inspired Training Method for Rerankers and Embedding Models},
      author={Nicholas Pipitone and Ghita Houir Alami and Advaith Avadhanam and Anton Kaminskyi and Ashley Khoo},
      year={2025},
      eprint={2509.12541},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.12541},
}

Text Model¶

Instruction Model¶

AQ-MedAI/Diver-Retriever-0.6B¶

AQ-MedAI/Diver-Retriever-1.7B¶

AQ-MedAI/Diver-Retriever-4B¶

AQ-MedAI/Diver-Retriever-4B-1020¶

Alibaba-NLP/gte-Qwen1.5-7B-instruct¶

Alibaba-NLP/gte-Qwen2-1.5B-instruct¶

Alibaba-NLP/gte-Qwen2-7B-instruct¶

BAAI/bge-base-en¶

BAAI/bge-base-en-v1.5¶

BAAI/bge-base-zh¶

BAAI/bge-base-zh-v1.5¶

BAAI/bge-large-en¶

BAAI/bge-large-en-v1.5¶

BAAI/bge-large-zh¶

BAAI/bge-large-zh-v1.5¶

BAAI/bge-small-en¶

BAAI/bge-small-en-v1.5¶

BAAI/bge-small-zh¶

BAAI/bge-small-zh-v1.5¶

BMRetriever/BMRetriever-1B¶

BMRetriever/BMRetriever-2B¶

BMRetriever/BMRetriever-410M¶

BMRetriever/BMRetriever-7B¶

BeastyZ/e5-R-mistral-7b¶

BidirLM/BidirLM-0.6B-Embedding¶

BidirLM/BidirLM-1.7B-Embedding¶

BidirLM/BidirLM-1B-Embedding¶

BidirLM/BidirLM-270M-Embedding¶

ByteDance-Seed/Seed1.5-Embedding¶

Bytedance/Seed1.6-embedding-1215¶

Cohere/Cohere-embed-english-light-v3.0¶

Cohere/Cohere-embed-english-v3.0¶

Cohere/Cohere-embed-multilingual-light-v3.0¶

Cohere/Cohere-embed-multilingual-v3.0¶

Cohere/Cohere-embed-v5.0-fast¶

Cohere/Cohere-embed-v5.0-pro¶

GeoGPT-Research-Project/GeoEmbedding¶

GritLM/GritLM-7B¶

GritLM/GritLM-8x7B¶

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1¶

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5¶

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2¶

Hanno-Labs/dinghy-law-0.6b-v1¶

Hanno-Labs/dinghy-law-4b-v1¶

Hanno-Labs/dinghy-law-8b-v1¶

ICT-TIME-and-Querit/BOOM_4B_v1¶

ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1¶

IEITYuan/Yuan-embedding-2.0-en¶

KaLM-Embedding/KaLM-Reranker-V1-Large¶

KaLM-Embedding/KaLM-Reranker-V1-Large-R2¶

KaLM-Embedding/KaLM-Reranker-V1-Nano¶

KaLM-Embedding/KaLM-Reranker-V1-Nano-R2¶

KaLM-Embedding/KaLM-Reranker-V1-Small¶

KaLM-Embedding/KaLM-Reranker-V1-Small-R2¶

KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5¶

Kingsoft-LLM/QZhou-Embedding¶

Kingsoft-LLM/QZhou-Embedding-Zh¶

KiteFishAI/Nano-Em1-0.6B-v2¶

KiteFishAI/Nano-Em1-0.6B-v2.1¶

LingoIITGN/FlowVec-v1¶

LingoIITGN/qwen-indic-v1¶

Linq-AI-Research/Linq-Embed-Mistral¶

LiquidAI/LFM2.5-Embedding-350M¶

ManiacLabs/miniac-embed¶

McGill-NLP/AfriE5-Large-instruct¶

McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised¶

McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse¶

McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised¶

McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-unsup-simcse¶

McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised¶

McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse¶

McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-supervised¶

McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse¶

MongoDB/mdbr-leaf-ir¶

MongoDB/mdbr-leaf-mt¶

NGA-KR/ko-embed-midm¶

NGA-KR/ko-embed-v0¶

NovaSearch/jasper_en_vision_language_v1¶

`AQ-MedAI/Diver-Retriever-0.6B`¶

`AQ-MedAI/Diver-Retriever-1.7B`¶

`AQ-MedAI/Diver-Retriever-4B`¶

`AQ-MedAI/Diver-Retriever-4B-1020`¶

`Alibaba-NLP/gte-Qwen1.5-7B-instruct`¶

`Alibaba-NLP/gte-Qwen2-1.5B-instruct`¶

`Alibaba-NLP/gte-Qwen2-7B-instruct`¶

`BAAI/bge-base-en`¶

`BAAI/bge-base-en-v1.5`¶

`BAAI/bge-base-zh`¶

`BAAI/bge-base-zh-v1.5`¶

`BAAI/bge-large-en`¶

`BAAI/bge-large-en-v1.5`¶

`BAAI/bge-large-zh`¶

`BAAI/bge-large-zh-v1.5`¶

`BAAI/bge-small-en`¶

`BAAI/bge-small-en-v1.5`¶

`BAAI/bge-small-zh`¶

`BAAI/bge-small-zh-v1.5`¶

`BMRetriever/BMRetriever-1B`¶

`BMRetriever/BMRetriever-2B`¶

`BMRetriever/BMRetriever-410M`¶

`BMRetriever/BMRetriever-7B`¶

`BeastyZ/e5-R-mistral-7b`¶

`BidirLM/BidirLM-0.6B-Embedding`¶

`BidirLM/BidirLM-1.7B-Embedding`¶

`BidirLM/BidirLM-1B-Embedding`¶

`BidirLM/BidirLM-270M-Embedding`¶

`ByteDance-Seed/Seed1.5-Embedding`¶

`Bytedance/Seed1.6-embedding-1215`¶

`Cohere/Cohere-embed-english-light-v3.0`¶

`Cohere/Cohere-embed-english-v3.0`¶

`Cohere/Cohere-embed-multilingual-light-v3.0`¶

`Cohere/Cohere-embed-multilingual-v3.0`¶

`Cohere/Cohere-embed-v5.0-fast`¶

`Cohere/Cohere-embed-v5.0-pro`¶

`GeoGPT-Research-Project/GeoEmbedding`¶

`GritLM/GritLM-7B`¶

`GritLM/GritLM-8x7B`¶

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1`¶

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5`¶

`HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2`¶

`Hanno-Labs/dinghy-law-0.6b-v1`¶

`Hanno-Labs/dinghy-law-4b-v1`¶

`Hanno-Labs/dinghy-law-8b-v1`¶

`ICT-TIME-and-Querit/BOOM_4B_v1`¶

`ICT-TIME-and-Querit/ICT-TIME-and-Querit-embedding-v1`¶

`IEITYuan/Yuan-embedding-2.0-en`¶

`KaLM-Embedding/KaLM-Reranker-V1-Large`¶

`KaLM-Embedding/KaLM-Reranker-V1-Large-R2`¶

`KaLM-Embedding/KaLM-Reranker-V1-Nano`¶

`KaLM-Embedding/KaLM-Reranker-V1-Nano-R2`¶

`KaLM-Embedding/KaLM-Reranker-V1-Small`¶

`KaLM-Embedding/KaLM-Reranker-V1-Small-R2`¶

`KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5`¶

`Kingsoft-LLM/QZhou-Embedding`¶

`Kingsoft-LLM/QZhou-Embedding-Zh`¶

`KiteFishAI/Nano-Em1-0.6B-v2`¶

`KiteFishAI/Nano-Em1-0.6B-v2.1`¶

`LingoIITGN/FlowVec-v1`¶

`LingoIITGN/qwen-indic-v1`¶

`Linq-AI-Research/Linq-Embed-Mistral`¶

`LiquidAI/LFM2.5-Embedding-350M`¶

`ManiacLabs/miniac-embed`¶

`McGill-NLP/AfriE5-Large-instruct`¶

`McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-supervised`¶

`McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp-unsup-simcse`¶

`McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised`¶

`McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-unsup-simcse`¶

`McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised`¶

`McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcse`¶

`McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-supervised`¶

`McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp-unsup-simcse`¶

`MongoDB/mdbr-leaf-ir`¶

`MongoDB/mdbr-leaf-mt`¶

`NGA-KR/ko-embed-midm`¶

`NGA-KR/ko-embed-v0`¶

`NovaSearch/jasper_en_vision_language_v1`¶

`NovaSearch/stella_en_1.5B_v5`¶

`NovaSearch/stella_en_400M_v5`¶