ESM3 open (esm3-sm-open-v1)

ESM3 open (esm3-sm-open-v1) code and weights licenses

Commercial use of ESM3 open (esm3-sm-open-v1)

Code

Yes · Permissive

Weights

Yes · Permissive

The code license and the weights license stand apart; a verdict on one does not carry over to the other. Quoted statements and their sources are in the license section above.

Verdicts record what sources state and are not legal advice.

Limits on outputs

• The function decoder was filtered for potentially harmful keywords.
  huggingface.co · 2026-11-13

  The function decoder has been filtered for potentially harmful keywords.

  https://huggingface.co/biohub/esm3-sm-open-v1 · Dataset page · checked 2026-11-13

• The README states the models are available under the MIT licence and asks users to follow Biohub's Acceptable Use Policy.
  github.com · 2026-11-13

  Please follow our [Acceptable Use Policy](https://biohub.org/acceptable-use-policy/) when using the model.

  https://github.com/Biohub/esm/blob/main/README.md · Dataset page · checked 2026-11-13

Training data

• 2.78 billion natural proteins with synthetic augmentation The model card says the model is trained on 2.78 billion natural proteins, which with synthetic augmentation totaled 3.15 billion protein sequences, 236 million protein structures, 539 million function-annotated proteins and 771 billion tokens.
  huggingface.co · 2026-11-13

  `esm3-sm-open-v1` is trained on 2.78 billion natural proteins. With synthetic data augmentation, this led to 3.15 billion protein sequences, 236 million protein structures, and 539 million proteins with function annotations, totaling 771 billion tokens.

  https://huggingface.co/EvolutionaryScale/esm3-sm-open-v1/raw/main/README.md · README · checked 2026-11-13

• training data Trained on 2.78 billion natural proteins, expanded by synthetic augmentation to 3.15 billion sequences, 236 million structures and 539 million function-annotated proteins (771 billion tokens).
  huggingface.co · 2026-11-13

  esm3-sm-open-v1 is trained on 2.78 billion natural proteins.

  https://huggingface.co/biohub/esm3-sm-open-v1 · Dataset page · checked 2026-11-13

• training data Virus-related data and some proteins from organisms on the USDA Select Agents and Toxins list were removed from training data.
  huggingface.co · 2026-11-13

  data related to viruses has been removed from the training dataset

  https://huggingface.co/biohub/esm3-sm-open-v1 · Dataset page · checked 2026-11-13

Running ESM3 open (esm3-sm-open-v1)

• Weights downloadhuggingface.co
• Third-party hostinggithub.com

ESM3 open (esm3-sm-open-v1) versions

• ESM-3 (2025-01-16): code —, weights —
  github.com · 2026-11-13

  ESM-3 Open Model

  https://github.com/Biohub/esm/blob/1b3e08025b/LICENSE.md · Dataset page · checked 2026-11-13

• unspecified (2025-01-16): code —, weights —
  github.com · 2026-11-13

  Just remember to maintain the same license terms and release under the ESM name.

  https://github.com/Biohub/esm/blob/1b3e08025b/LICENSE.md · Dataset page · checked 2026-11-13

• 304 (2026-05-27): code —, weights —
  github.com · 2026-11-13

  Update esm repo for ESMC paper ( #304 )

  https://github.com/Biohub/esm/commit/c94ed8d763 · Dataset page · checked 2026-11-13

ESM3 open (esm3-sm-open-v1) official download addresses

• Repository or releasehttps://huggingface.co/EvolutionaryScale/esm3-sm-open-v1
• Weights pagehttps://huggingface.co/EvolutionaryScale/esm3-sm-open-v1
• License filehttps://raw.githubusercontent.com/evolutionaryscale/esm/main/LICENSE.md