AI models
Boltz-2
Published
Jun 6, 2025
Boltz-2 is an AI model developed by Massachusetts Institute of Technology (MIT), Recursion Pharmaceuticals, ETH Zurich and Valence Labs (United States, Switzerland and Canada), first published in June 2025. It works in the biology domain, on tasks such as protein interaction prediction and protein-ligand binding affinity prediction.
Epoch AI has no training-compute estimate for this model. Training ran on 188 NVIDIA A100,NVIDIA H100 NVL.
Access: Open weights (unrestricted). Its weights are openly available.
Full record
- Organization
- Massachusetts Institute of Technology (MIT), Recursion Pharmaceuticals, ETH Zurich, Valence Labs
- Country of organization
- United States, Switzerland, Canada
- Domain
- Biology
- Task
- Protein interaction prediction, Protein-ligand binding affinity prediction
- Training hardware
- NVIDIA A100, NVIDIA H100 NVL
- Chips used
- 188
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 0
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models