TorchFold on pretrained AlphaFold 3 parameters
A TorchFold setting that loads the official pretrained AlphaFold 3 parameters as the frozen predictor weights.
Results are recorded on linked configurations and versions of this configuration. Their settings and evaluations are kept separate below.
Results on linked records
This configuration has no results of its own in this release. 6 linked records have results. They are not assigned to the underlying configuration: each record keeps its own settings and evaluations, and its scores are on its own page.
- TorchCraft minibinder design, raw output Configuration · uses this model · 4 evaluations · 4 results
- TorchCraft on A100 with cuequivariance kernels Configuration · uses this model · 5 evaluations · 5 results
- TorchCraft on A100 without cuequivariance kernels Configuration · uses this model · 5 evaluations · 5 results
- TorchCraft on Ascend 910B with fused attention Configuration · uses this model · 5 evaluations · 5 results
- TorchCraft on Ascend 910B without fused attention Configuration · uses this model · 5 evaluations · 5 results
- TorchCraft framework-conditioned VHH design, raw output Configuration · uses this model · 4 evaluations · 4 results
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Model Capabilities & Hardware Requirements
Deployment facts recorded for TorchFold on pretrained AlphaFold 3 parameters. Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: Pretrained AlphaFold 3 weights, through the TorchFold implementation; TorchX GPU tree at commit ebf9dc6676ecb1be505bc72f87de408995f0d8fd
Use this configuration
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
3 source records and release history
- TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Original source · arXiv:2609.19770v1, submitted 17 September 2026
- TorchX repository README at commit ebf9dc6 · Original source · commit ebf9dc6676ecb1be505bc72f87de408995f0d8fd, authored 2026-11-04T07:22:24Z
- TorchX torchcraft_gpu/README.md at commit ebf9dc6 · Original source · commit ebf9dc6676ecb1be505bc72f87de408995f0d8fd
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID torchcraft-20261115-config-torchfold-af3-parameters.
Source locator: Abstract; Section 1 final paragraph; Appendix A.1.1 'All designs reported in this study used pretrained AF3 weights'; Appendix A.4.2; Figure 1 caption; README section 'Checkpoints'
Related records
- configuration of: TorchFold
- uses model: AlphaFold 3
- subject: TorchFold on pretrained AlphaFold 3 parameters: The AlphaFold 3 parameters come under DeepMind's own terms
- uses model: TorchCraft disulfide-linked cyclic-peptide design with ProteinMPNN polishing
- uses model: TorchCraft disulfide-linked cyclic-peptide design, raw output
- uses model: TorchCraft head-to-tail cyclic-peptide design with ProteinMPNN polishing
- uses model: TorchCraft head-to-tail cyclic-peptide design, raw output
- uses model: TorchCraft ligand-conditioned pocket design with LigandMPNN redesign
- uses model: TorchCraft ligand-conditioned pocket design, raw output
- uses model: TorchCraft minibinder design with ProteinMPNN polishing
- uses model: TorchCraft minibinder design, raw output
- uses model: TorchCraft on A100 with cuequivariance kernels
- uses model: TorchCraft on A100 without cuequivariance kernels
- uses model: TorchCraft on Ascend 910B with fused attention
- uses model: TorchCraft on Ascend 910B without fused attention
- uses model: TorchCraft VHH design with AbMPNN polishing
- uses model: TorchCraft framework-conditioned VHH design, raw output
How to cite
TorchFold on pretrained AlphaFold 3 parameters. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/torchcraft-20261115-config-torchfold-af3-parameters/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence