[GH-ISSUE #671] NVIDIA/CUDA support for q8_0 models seems to be disabled #302

Closed
opened 2026-04-12 09:50:46 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @spaceemotion on GitHub (Oct 2, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/671

Originally assigned to: @BruceMacD on GitHub.

When loading a model like open-orca-platypus2 it works with the latest tag, but when trying to run q8_0 variants the layers don't get offloaded to the GPU properly.

Originally created by @spaceemotion on GitHub (Oct 2, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/671 Originally assigned to: @BruceMacD on GitHub. When loading a model like `open-orca-platypus2` it works with the `latest` tag, but when trying to run `q8_0` variants the layers don't get offloaded to the GPU properly.
GiteaMirror added the bug label 2026-04-12 09:50:46 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#302