Skip to content

Image Model

21 Models

Non-instruction Model

facebook/dinov2-base

License: apache-2.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
86.6M 768 not specified 330.0 MB 2023-07-18 eng-Latn
Citation
@misc{oquab2023dinov2,
      title={DINOv2: Learning Robust Visual Features without Supervision},
      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
      year={2023},
      eprint={2304.07193},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

facebook/dinov2-giant

License: apache-2.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
1.1B 1536 not specified 4.2 GB 2023-07-18 eng-Latn
Citation
@misc{oquab2023dinov2,
      title={DINOv2: Learning Robust Visual Features without Supervision},
      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
      year={2023},
      eprint={2304.07193},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

facebook/dinov2-large

License: apache-2.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
304.4M 1024 not specified 1.1 GB 2023-07-18 eng-Latn
Citation
@misc{oquab2023dinov2,
      title={DINOv2: Learning Robust Visual Features without Supervision},
      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
      year={2023},
      eprint={2304.07193},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

facebook/dinov2-small

License: apache-2.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
22.1M 384 not specified 84.0 MB 2023-07-18 eng-Latn
Citation
@misc{oquab2023dinov2,
      title={DINOv2: Learning Robust Visual Features without Supervision},
      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
      year={2023},
      eprint={2304.07193},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

facebook/webssl-dino1b-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
1.1B 1536 not specified 4.2 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino2b-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.1B 2688 not specified 7.8 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino2b-heavy2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.1B 2688 not specified 7.8 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino2b-light2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.1B 2688 not specified 7.8 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino300m-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
303.7M 1024 not specified 1.1 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino3b-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.9B 3072 not specified 11.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino3b-heavy2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.9B 3072 not specified 11.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino3b-light2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
2.9B 3072 not specified 11.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino5b-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
4.9B 3584 not specified 18.4 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino7b-full8b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
6.5B 4096 not specified 24.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino7b-full8b-378

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
6.5B 4096 not specified 24.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-dino7b-full8b-518

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
6.5B 4096 not specified 24.0 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-mae1b-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
1.1B 1536 not specified 4.2 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-mae300m-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
304.4M 1024 not specified 1.1 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

facebook/webssl-mae700m-full2b-224

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
632.4M 1280 not specified 2.4 GB 2025-04-24 eng-Latn
Citation
@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning},
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

nyu-visionx/moco-v3-vit-b

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
86.6M 768 not specified 330.0 MB 2024-06-03 eng-Latn
Citation
@Article{chen2021mocov3,
    author  = {Xinlei Chen* and Saining Xie* and Kaiming He},
    title   = {An Empirical Study of Training Self-Supervised Vision Transformers},
    journal = {arXiv preprint arXiv:2104.02057},
    year    = {2021},
}

nyu-visionx/moco-v3-vit-l

License: cc-by-nc-4.0 • Learn more →

Parameters Emb. Dim Max Tokens Memory Released Languages
304.0M 1024 not specified 1.1 GB 2024-06-03 eng-Latn
Citation
@Article{chen2021mocov3,
    author  = {Xinlei Chen* and Saining Xie* and Kaiming He},
    title   = {An Empirical Study of Training Self-Supervised Vision Transformers},
    journal = {arXiv preprint arXiv:2104.02057},
    year    = {2021},
}