Skip to navigation

Support Matrix

View as Markdown

Models

GenMol NIM supports a generic model profile operates with any NVIDIA GPU that has sufficient memory capacity.

PrecisionDisk SpaceProfile ID
FP32340MBa525212dd4373ace3be568a38b5d189a6fb866e007adf56e750ccd11e896b036

Supported Hardware

GPU

GPUGPU Memory (GB)PrecisionProfile# of GPUs
H10080FP32generic1
A10040 or 80FP32generic1
L40S48FP32generic1
A10G24FP32generic1
A600048FP32generic1

Minimum GPU Memory

16GB

Disk Space

NVIDIA recommends at least 20GB disk space for the container and model.

CUDA Compute Capability

This NIM requires CUDA Compute Capability of ≥ 7.0.

Supported Software

NVIDIA Driver and Prerequisite

PrerequisiteVersionLink
NVIDIA Graphic Drivers for linux535.104.05 or abovehttps://www.nvidia.com/en-us/drivers/unix/
NVIDIA Container Toolkitlatesthttps://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
DockerlatestUbuntu, CentOS, Debian: https://docs.docker.com/engine/install/
Rocky Linux: https://docs.rockylinux.org/gemstones/containers/docker/