Error when install self-hosted-ai-starter-kit, could not select device driver "nvidia"

When attempting to run the “self-hosted-ai-starter-kit” with the following commands:

<<<
git clone GitHub - n8n-io/self-hosted-ai-starter-kit: The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.
cd self-hosted-ai-starter-kit
docker compose --profile gpu-nvidia up

It fails with the error message:

Error response from daemon: could not select device driver “nvidia” with capabilities: [[gpu]]

Environment:
ubuntu 24.04 lts with updates
docker-ce, latest
Nvidia RTX 4060 Ti
Dell XPS 8960

It looks like your topic is missing some important information. Could you provide the following if applicable.

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:

Hi @jnhuffman81

Thanks for posting here and welcome to the community! :cupcake:

This error sounds like your Docker setup is unable to access the NVIDIA GPU. You can try to follow this guide here to install the NVIDIA Container Toolkit:

This is the same as the information I found by searching over the weekend. I hope to try it later today. Thanks for the reply.

1 Like