Supported Hardware
Each prediction runs on a single GPU. Starting in 1.6.0, a container given more than one GPU serves requests from all of them concurrently; refer to Configuration Alternatives.
GPU
The OpenFold3 NIM is supported to run on the GPU configurations below.
The GB10 features 128 GB of LPDDR5x unified memory shared between CPU and GPU, providing a single memory space across the NVIDIA Grace Blackwell Superchip architecture. It is listed as 1 rather than 1 or more because a DGX Spark carries a single GB10 superchip. There is no second GPU for the NIM to start a worker on.
Storage
NVIDIA recommends at least 80 GB of disk space.
The container is roughly 11 GB to download and approximately 40 GB once unpacked. Model parameters are not included in the container; they are downloaded on first run into the NIM cache directory, which needs a further 15 GB. Refer to Getting Started for how to set the cache location.
CPU and System Memory
- At least 64 GB of RAM
- A CPU with at least 8 available cores