Run a command on your GNU/Linux dedicated Nvidia GPU (e.g. ollama)
To make sure a command (CLI) is using your NVIDIA GPU in GNU/Linux, you can use the environment variables __NV_PRIME_RENDER_OFFLOAD=1 and __GLX_VENDOR_LIBRARY_NAME=nvidia before your command.
Example:
Example:
__NV_PRIME_RENDER_OFFLOAD=1 __GLX_VENDOR_LIBRARY_NAME=nvidia ollama run orca-mini
You can also verify that it works by running:
__NV_PRIME_RENDER_OFFLOAD=1 __GLX_VENDOR_LIBRARY_NAME=nvidia glxinfo | grep vendor
Which should output something like:
server glx vendor string: NVIDIA Corporation client glx vendor string: NVIDIA Corporation OpenGL vendor string: NVIDIA Corporation
