AI Potluck
Back to Gap Map Model components / Scientific AI models

Boltz

Jeremy Wohlwend
open source / Overall score: 2.7

Boltz 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
5.0
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.

Adoption

2 medium confidence
2.0

boltz-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.

Capability

3 high confidence
3.0

Two 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.

Verified 2026-09-10