LocalFold runs AlphaFold3, Boltz-2 and more protein folding models in your browser via WebGPU
sokrypton · x · 2026-09-17
A new WebGPU port brings protein structure prediction to local machines: LocalFold (localfold.org) lets users drop in a file and fold with AF3, OpenBind-0, OpenDDE, Boltz-2, Protenix-v2, IntelliFold-2, RoseTTAFold3 and more, with tunable recycles, samplers and MSA settings.
The author (sokrypton) also teased ColabFold2, a JAX-based integration of alphafold3, openfold3, intellifold2, protenix2, boltz2, rosettafold3, chai1, esmfold2 and openbind0, shipped as a Colab notebook and pip package. The WebGPU port is highly experimental — expect drained batteries, overheating laptops and heavy data usage. The effort started with Martin Steinegger's AF2 port to WebGPU.
More from Research
- Harvard study suggests smartphones could predict suicide risk with striking accuracy — pshrink · 2026-09-17
- Study of 7 models across Claude Code, Codex, Pi: harness barely affects success but swings cost — DavideCrapis · 2026-09-17
- Neuroevolved value function solves Tetris at world-record speed in your browser — NathanWilbanks_ · 2026-09-17
- Polymarket atomicity gap: 1.8M reverted trades expose ghost-filled order attack — chaumian · 2026-09-17
- NeurIPS 2026 opens financial aid and volunteer applications, due Oct 6 — NeurIPSConf · 2026-09-17
- Classifying 1,018 AI Papers for $4: A Two-Model Pipeline at 256ms Median Latency — nutlope · 2026-09-17