github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 13:42:25 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14765] Not work on rx9060xt #56058

New Issue
Closed
opened 2026-04-29 10:12:29 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 10:12:29 -05:00
Owner
Copy Link

Originally created by @ByPythonCoder on GitHub (Mar 10, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14765

Describe the bug

Ollama (v0.17.7/v0.17.8) fails to offload layers to the GPU on the new AMD Radeon RX 9060 XT (GFX1200 / Navi 44). The system is running Arch Linux with mesa-git (Mesa 26.1.0-devel).

System Information

  • OS: Arch Linux
  • GPU: AMD Radeon RX 9060 XT (GFX1200 / RADV)
  • Kernel: 7.0 cachyos-rc3
  • Mesa Version: 26.1.0_devel (mesa-git)
  • Ollama Version: 0.17.7

Log Output

Even with OLLAMA_VULKAN=1, the runner falls back to CPU:
level=INFO source=ggml.go:494 msg="offloaded 0/35 layers to GPU"
vulkaninfo correctly identifies the device:
deviceName = AMD Radeon RX 9060 XT (RADV GFX1200)

Additional Context

The GFX1200 architecture seems to be missing from the supported GPU discovery list in the current llama.cpp/ggml integration.

Originally created by @ByPythonCoder on GitHub (Mar 10, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14765 ### Describe the bug Ollama (v0.17.7/v0.17.8) fails to offload layers to the GPU on the new AMD Radeon RX 9060 XT (GFX1200 / Navi 44). The system is running Arch Linux with mesa-git (Mesa 26.1.0-devel). ### System Information - **OS:** Arch Linux - **GPU:** AMD Radeon RX 9060 XT (GFX1200 / RADV) - **Kernel:** 7.0 cachyos-rc3 - **Mesa Version:** 26.1.0_devel (mesa-git) - **Ollama Version:** 0.17.7 ### Log Output Even with `OLLAMA_VULKAN=1`, the runner falls back to CPU: `level=INFO source=ggml.go:494 msg="offloaded 0/35 layers to GPU"` `vulkaninfo` correctly identifies the device: `deviceName = AMD Radeon RX 9060 XT (RADV GFX1200)` ### Additional Context The GFX1200 architecture seems to be missing from the supported GPU discovery list in the current llama.cpp/ggml integration.
GiteaMirror commented 2026-04-29 10:12:30 -05:00
Author
Owner
Copy Link

@Kangaroux commented on GitHub (Mar 11, 2026):

Have you tried https://docs.ollama.com/gpu#overrides-on-linux

<!-- gh-comment-id:4035863219 --> @Kangaroux commented on GitHub (Mar 11, 2026): Have you tried https://docs.ollama.com/gpu#overrides-on-linux
GiteaMirror commented 2026-04-29 10:12:31 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 11, 2026):

Release 0.17.8 updates Linux to ROCm v7 which covers support for this GPU. Please give the RC a try and let us know if you run into any problems.

<!-- gh-comment-id:4041965932 --> @dhiltgen commented on GitHub (Mar 11, 2026): Release 0.17.8 updates Linux to ROCm v7 which covers support for this GPU. Please give the [RC a try](https://github.com/ollama/ollama/blob/main/docs/linux.mdx#installing-specific-versions) and let us know if you run into any problems.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#56058
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?