∿foldscout.

MODEL INTELLIGENCE / VERIFIED RESEARCH

RFdiffusion3 (RFD3)

All-atom diffusion for designing protein interfaces, ligand contacts and catalytic motifs.

Developer: Institute for Protein Design / RosettaCommons, University of Washington

Commercial OK
COMMERCIAL RIGHTSCommercial OK
COMMERCIAL FEENo license fee identified
COMPUTESingle Gpu
MODEL WEIGHTSAvailable

Overview

Developer
Institute for Protein Design / RosettaCommons, University of Washington
Category
de novo binder and protein design
Commercial rights
Commercial OK
License fee
No license fee identified
Open weights
Yes
Last verified
2026-10-16
Added to FoldScout
2026-10-16

Capabilities

An atom-level RFdiffusion generative design model for proteins, protein-protein interfaces, ligands, nucleic-acid binders and enzyme active sites. Input: target structure and design restraints in JSON/YAML; output: candidate designed coordinates and sequences. Predicted designs require sequence/structure and experimental validation.

When to use it

Choose for all-atom constrained binder, enzyme motif or small-molecule interaction design; it is a generation model, not an empirical affinity measurement. Official installation suggests NVIDIA GPUs; CPU is possible but slow.

Compute

Compute classification: single-gpu. This is a planning estimate, not a throughput benchmark; check the linked model installation documents for exact requirements.

Commercial licensing

Commercial permission — Commercial OK

The Foundry LICENSE.md explicitly includes source code and model weights referenced for download in the README. BSD-3-Clause allows commercial use while requiring preservation of notices and no implied endorsement. Separately review external tools and datasets in your workflow.

License fee — No license fee identified

No commercial licensing fee for Foundry code or the officially referenced RFD3 checkpoint under BSD-3-Clause. Cloud/GPU compute, extra software, and service fees are separate.

Free downloads do not necessarily permit company use. Code, checkpoints, external dependencies and compute expenses require separate review.

Official references

From computational design to experimental evidence

Validate your designed binder.

Seq2Study connects AI-designed proteins and antibodies with expression, affinity, stability and developability testing.

Explore Seq2Study ↗