Unverified50% confidenceFactExact time
The containerd runtime built into K3s does not, by default, expose the host's PCI hardware (such as an NVIDIA GPU) to containers.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf Ollama in a K3s container cannot see the /dev/nvidia* device nodes, it will be unable to load the CUDA runtime and will thus fall back to CPU inference.68% similarUnverifiedWhen only tensorflow-macos is installed, no GPU device appears in the device enumeration and computation can only run on the CPU; only after correctly installing tensorflow-metal will TensorFlow detect the Metal GPU device.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057664API
curl https://kongchang.com/api/v1/knowledge/claims/1057664MCP
get_claim(id=1057664)