OpenFold3 Structure Prediction

Prerequisites

Requirement	Minimum	Recommended
Python	3.10+	3.11
CUDA	12.1+	12.4+
GPU VRAM	24GB	80GB (H100)
RAM	32GB	64GB
Disk (weights)	3GB	-

How to run

Installation

pip install 'openfold3[cuequivariance]==0.4.1'

The default attention kernel is DeepSpeed DS4Sci_EvoformerAttention. If DeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no build-from-source) by overriding the eval memory settings in model_config.py (use_deepspeed_evo_attention: False, use_cueq_triangle_kernels: True). Some pre-built environments already ship this override; check before re-patching.

Weights

Apache-2.0, ~2.3 GB from HF OpenFold/OpenFold3. The repo is gated (auto-approval), accept the access form on the HF model page and authenticate (huggingface-cli login or HF_TOKEN) before downloading:

export OPENFOLD_CACHE=~/.openfold3
huggingface-cli download OpenFold/OpenFold3 checkpoints/of3-p2-155k.pt \
  --local-dir "$OPENFOLD_CACHE"

run_openfold will also auto-download to $OPENFOLD_CACHE on first run if egress is open and HF credentials are available (either HF_TOKEN or a prior huggingface-cli login) with repo access granted. The interactive setup_openfold helper exists but prompts on stdin; prefer the explicit download above for non-interactive runs.

Running

export OPENFOLD_CACHE=/path/to/cache
run_openfold predict \
  --query_json=queries.json \
  --output-dir out/ \
  --use-msa-server false \
  --use-templates false

run_openfold discovers the checkpoint under $OPENFOLD_CACHE automatically. Only pass --inference-ckpt-path <file.pt> if you have a non-standard layout or multiple checkpoints and need to pin one explicitly.