Supported Hardware

The OpenFold3 NIM is configured to run on a single GPU, and supports different sequence length ranges depending on the inference backend:

• PyTorch backend: Supports sequences from 2 to 4096 amino acids

• TensorRT-BioNeMo backend: Supports sequences from 4 to 2048 amino acids (optimized for faster inference)

GPU

The OpenFold3 NIM is supported to run on the GPU configurations below.

GPU	GPU Memory	# of GPUs
NVIDIA H100 80GB HBM3	80GB	[1]
NVIDIA H100 PCIe	80GB	[1]
NVIDIA A100-SXM4-80GB	80GB	[1]
NVIDIA A100 80GB PCIe	80GB	[1]
NVIDIA H200	141GB	[1]
NVIDIA B200	180GB	[1]
NVIDIA L40S	48GB	[1]

Storage

NVIDIA recommends at least 80GB of disk space. The container is roughly 61GB, which includes the OpenFold3 model parameters (~6GB) and TensorRT optimized inference engines.

CPU and System Memory

• At least 64 GB of RAM

• A CPU with at least 8 available cores