Boltz
Jeremy WohlwendBoltz is a family of biomolecular interaction models. Boltz-1 was the first fully open-source model to approach AlphaFold 3 accuracy, and Boltz-2 jointly models complex structure and binding affinity, reporting a log10(IC50) value alongside a binder-versus-decoy probability. It runs from a YAML specification of the complex, optionally pulling MSAs from a ColabFold server.
Code and weights are both MIT, and the training corpus, preprocessing pipeline and training configs are published for Boltz-1; the equivalents for Boltz-2 are announced as coming but have not shipped. Verified 2026-09-10 via the GitHub API, the README, the LICENSE body, and the training documentation.
Openness
5 high confidence- weights
- open(MIT weights downloaded by the boltz package, covering Boltz-1 and Boltz-2)
- data
- open(pre-processed RCSB and OpenFold structures and MSAs published for download, with instructions for reprocessing raw data)
- code
- open(training script and structure and confidence model configs under scripts/train, alongside a training guide)
- license
- MIT(OSI)
Boltz reaches the top rung on the strength of the Boltz-1 release, where the corpus, the preprocessing pipeline, the training configs and MIT weights all shipped together. The Boltz-2 equivalents are marked coming soon and have not landed, so the pipeline a reader can actually run trails the model they would want to train; the license and the weights, which is what the rung turns on, cover both.
- https://raw.githubusercontent.com/jwohlwend/boltz/main/README.md recorded 2026-09-10
"All the code and weights are provided under MIT license, making them freely available for both academic and commercial uses"; a Training section pointing at docs/training.md for retraining.
- https://raw.githubusercontent.com/jwohlwend/boltz/main/LICENSE recorded 2026-09-10
MIT License body, Copyright (c) 2024 Jeremy Wohlwend, Gabriele Corso, Saro Passaro.
- https://raw.githubusercontent.com/jwohlwend/boltz/main/docs/training.md recorded 2026-09-10
Download links for the pre-processed RCSB and OpenFold structures and MSAs and the ligand symmetry file, instructions for reprocessing raw data, and template training configs for the structure and confidence models under scripts/train/configs; Boltz-2 training information is marked coming soon.
Adoption
2 medium confidenceboltz-community/boltz-1 and boltz-community/boltz-2 are the Hub repositories the package resolves weights from, but both report zero downloads because src/boltz/main.py fetches resolve/main/*.ckpt directly rather than through the Hub API, so the counter measures the API path and not the reach. 4,202 GitHub stars are the last-resort signal, on the same footing as aurora-weather and openfold.
- https://api.github.com/repos/jwohlwend/boltz recorded 2026-09-10
stargazers_count: 4202; archived: false; fork: false.
- https://huggingface.co/api/models/boltz-community/boltz-2 recorded 2026-09-10
downloads: 0; likes: 16; gated: false; license mit — the Hub artifact exists and reports zero, which is what puts this band on stars rather than on usage_volume.
Capability
3 high confidenceTwo attributes. Adding binding affinity to structure prediction widens what Boltz-2 outputs without adding a scale or a design surface, so the second head is not a third attribute.
- https://raw.githubusercontent.com/jwohlwend/boltz/main/README.md recorded 2026-09-10
Inference takes a YAML specification of the biomolecules with an optional MSA server; the Training section documents retraining, and the affinity outputs are predicted values rather than generated molecules.
- https://raw.githubusercontent.com/jwohlwend/boltz/main/docs/training.md recorded 2026-09-10
"To run training, you will need to download a few pre-processed datasets", covering both structures and MSAs, with configuration templates for the structure and confidence models.
Verified 2026-09-10