Boltz-1
A-MIT
Structure PredictionComplex Predictionopen
Updated 3 weeks agoNextIn take
Boltz-1 is the open-source answer to AlphaFold3 — not as accurate on complexes, but you can actually deploy it. For most production teams, that tradeoff is obvious.
Specifications
| Architecture | Diffusion-based structure prediction with MSA conditioning |
| Parameters | ~300M |
| Training Data | PDB, UniRef, BFD — fully open training pipeline |
| License | MIT license. Fully open weights, code, and training pipeline. |
| Hardware | 1x A100 40GB for most predictions |
| Inference Cost | Self-hosted only — ~$0.02/prediction on cloud GPU |
| API Available | No |
| Weights Available | Yes |
Benchmark Performance
When to Use This
- +Production drug discovery pipelines where you need IP freedom and on-prem deployment
- +High-throughput structure prediction at scale
When NOT to Use This
- −When absolute peak accuracy on complexes matters more than accessibility
- −Ligand docking — use Boltz-2 or DiffDock instead
Production Readiness
production
Known Users
- Multiple pharma companies (undisclosed)
- Academic structural biology labs
Grade Rationale
A-
The best open-source structure prediction model available. Within striking distance of AF3 on accuracy while being fully deployable, modifiable, and free. The gap on complexes is real but narrowing.
Sources
Update History
2026-03-20Initial entry