Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Since updating to version 0.30.0, all models on my AMD Ryzen AI 9 HX 370 now run exclusively on the CPU.

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Code Example

Jun 02 17:53:17 ai systemd[1]: Started ollama.service - Ollama Service.
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.524Z level=INFO source=routes.go:1919 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL>
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.524Z level=INFO source=routes.go:1921 msg="Ollama cloud disabled: false"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.529Z level=INFO source=images.go:754 msg="total blobs: 129"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.532Z level=INFO source=images.go:761 msg="total unused blobs removed: 0"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.533Z level=INFO source=routes.go:1981 msg="Listening on [::]:11434 (version 0.30.0)"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.533Z level=INFO source=runner.go:55 msg="discovering available GPUs..."
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.544Z level=INFO source=model_list_cache.go:111 msg="model list cache hydration complete" models=43 failures=0 elapsed=10.577223ms
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.741Z level=INFO source=model_recommendations.go:177 msg="model recommendations cache sleep scheduled" wait=3h38m22.001425882s consec>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=runner.go:391 msg="dropping integrated GPU; to enable, set OLLAMA_IGPU_ENABLE=1" id=0 library=ROCm compute=gf>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=runner.go:391 msg="dropping integrated GPU; to enable, set OLLAMA_IGPU_ENABLE=1" id=0 library=Vulkan compute=>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=types.go:50 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama dri>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=routes.go:2031 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
lines 933-1000/1000 (END)
RAW_BUFFERClick to expand / collapse

What is the issue?

Since updating to version 0.30.0, all models on my AMD Ryzen AI 9 HX 370 now run exclusively on the CPU. I couldn't find anything in the documentation that said I needed to install anything extra for AMD ROCm 7. Everything still worked fine with version 0.24.0.

Relevant log output

Jun 02 17:53:17 ai systemd[1]: Started ollama.service - Ollama Service.
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.524Z level=INFO source=routes.go:1919 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL>
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.524Z level=INFO source=routes.go:1921 msg="Ollama cloud disabled: false"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.529Z level=INFO source=images.go:754 msg="total blobs: 129"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.532Z level=INFO source=images.go:761 msg="total unused blobs removed: 0"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.533Z level=INFO source=routes.go:1981 msg="Listening on [::]:11434 (version 0.30.0)"
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.533Z level=INFO source=runner.go:55 msg="discovering available GPUs..."
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.544Z level=INFO source=model_list_cache.go:111 msg="model list cache hydration complete" models=43 failures=0 elapsed=10.577223ms
Jun 02 17:53:17 ai ollama[1210908]: time=2026-06-02T17:53:17.741Z level=INFO source=model_recommendations.go:177 msg="model recommendations cache sleep scheduled" wait=3h38m22.001425882s consec>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=runner.go:391 msg="dropping integrated GPU; to enable, set OLLAMA_IGPU_ENABLE=1" id=0 library=ROCm compute=gf>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=runner.go:391 msg="dropping integrated GPU; to enable, set OLLAMA_IGPU_ENABLE=1" id=0 library=Vulkan compute=>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=types.go:50 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama dri>
Jun 02 17:53:18 ai ollama[1210908]: time=2026-06-02T17:53:18.102Z level=INFO source=routes.go:2031 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
lines 933-1000/1000 (END)

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.30.0

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING