Boltz-2
A-MIT
Structure PredictionMolecular DockingComplex Predictionopen
Updated 2 weeks agoNextIn take
Boltz-2 unifies structure prediction and docking into one open model — the workflow simplification alone makes it worth evaluating, even before you factor in the accuracy improvements over Boltz-1.
Specifications
| Architecture | Unified diffusion model for structure prediction and molecular docking |
| Parameters | ~400M |
| Training Data | PDB, PDBBind, UniRef, BFD — expanded ligand-protein complex data |
| License | MIT license. Fully open weights and training code. |
| Hardware | 1x A100 80GB recommended |
| Inference Cost | Self-hosted — ~$0.03/prediction on cloud GPU |
| API Available | No |
| Weights Available | Yes |
Benchmark Performance
| Benchmark | Score |
|---|---|
| PoseBusters | 72% valid |
| CASP15 | 0.83 GDT-TS (avg) |
When to Use This
- +End-to-end structure prediction plus docking in a single pipeline
- +Production workflows needing open-source ligand-protein modeling
When NOT to Use This
- −Pure protein structure prediction — Boltz-1 is lighter and nearly as good
- −When you need the absolute best docking accuracy regardless of openness
Production Readiness
pilot
Known Users
- Early adopters in biotech
- Academic drug discovery labs
Grade Rationale
A-
Extends Boltz-1 with integrated molecular docking in a single unified model. The first open model to seriously challenge AF3 across structure prediction and docking simultaneously. Still early but the trajectory is clear.
Sources
Update History
2026-03-25Initial entry