OpenFold3 vs Boltz

OpenFold3: Open-source AlphaFold3-style model predicting structures of proteins, nucleic acids and small-molecule complexes (preview release). Boltz: Open biomolecular interaction models (Boltz-1, Boltz-2) for complex structure and binding-affinity prediction.

Facts below come from each project's own website, repository and paper. We don't publish benchmark claims here; see the papers for evaluations.

FieldOpenFold3Boltz
TaskBiomolecular complex structure predictionStructure + binding-affinity prediction
ModalitiesProtein, RNA, DNA, small moleculesBiomolecular complexes
MSA requiredYes (ColabFold server or local)Optional (MSA server flag)
Open weightsYes (Hugging Face)Yes (MIT)
GPU needGPU; low-memory mode and multi-GPURecommended; CPU supported but much slower
LicenseApache-2.0MIT
PricingOpen sourceOpen source
Released2025-10-282024-11-17
Paper—Link
GitHubGitHubGitHub
GitHub stars8974,254
InterfacePackage, DockerPackage

License and commercial use

FieldOpenFold3Boltz
Code licenseApache-2.0MIT
Weights license—MIT
Commercial usePermissive (commercial OK)Permissive (commercial OK)
AnswerYes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. DetailsYes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details

Add more Protein structure & design tools to this comparison →

More Protein structure & design comparisons

← All Protein structure & design tools