ollama - 💡(How to fix) Fix ROCm on AMD Phoenix APUs (Radeon 780M iGPU) — HSA_OVERRIDE_GFX_VERSION required [2 comments, 2 participants]

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…
GitHub stats
ollama/ollama#15482Fetched 2026-04-11 06:12:30
View on GitHub
Comments
2
Participants
2
Timeline
2
Reactions
0
Timeline (top)
commented ×2

Error Message

This tells ROCm to treat the Phoenix APU as a supported gfx1100 target. Without it, the GPU sits idle — no error, no warning, just silent CPU fallback.

RAW_BUFFERClick to expand / collapse

Sharing a finding that might help others running Ollama on AMD Ryzen 7000/8000 series with integrated graphics (Phoenix APUs, Radeon 780M).

Out of the box, Ollama doesn't detect the iGPU and falls back to CPU. The fix is one environment variable: export HSA_OVERRIDE_GFX_VERSION=11.0.0

This tells ROCm to treat the Phoenix APU as a supported gfx1100 target. Without it, the GPU sits idle — no error, no warning, just silent CPU fallback.

After setting this + installing rocm-libs:

  • llama3.2:3b: ~20 tok/s (was ~1 tok/s on CPU)
  • phi4-mini: 14-20 tok/s
  • 31.4 GiB unified memory available (shared system RAM)

Discovered this on a Hetzner AX42-U (Ryzen 7 PRO 8700GE) where the iGPU isn't even listed in the server specs. Full benchmark writeup: https://cosmergon.com/reports/llm-benchmark-hetzner.html

Might be worth adding a note about Phoenix APUs to the ROCm/AMD section of the Ollama docs?

extent analysis

TL;DR

Setting the environment variable HSA_OVERRIDE_GFX_VERSION=11.0.0 allows Ollama to detect and utilize the integrated graphics on AMD Ryzen 7000/8000 series with Phoenix APUs.

Guidance

  • To enable iGPU detection, set the HSA_OVERRIDE_GFX_VERSION environment variable to 11.0.0 before running Ollama.
  • Ensure you have the rocm-libs installed, as this is required for the fix to work.
  • Verify that the iGPU is being utilized by checking the performance improvement, such as the increased token per second (tok/s) rate.
  • Consider adding a note to the Ollama documentation regarding the use of Phoenix APUs with ROCm/AMD to help other users.

Example

No explicit code example is provided, but the environment variable can be set using the command export HSA_OVERRIDE_GFX_VERSION=11.0.0 before running Ollama.

Notes

This fix is specific to AMD Ryzen 7000/8000 series with integrated graphics (Phoenix APUs) and may not apply to other hardware configurations.

Recommendation

Apply the workaround by setting the HSA_OVERRIDE_GFX_VERSION environment variable, as this has been shown to successfully enable iGPU detection and improve performance in Ollama.

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

ollama - 💡(How to fix) Fix ROCm on AMD Phoenix APUs (Radeon 780M iGPU) — HSA_OVERRIDE_GFX_VERSION required [2 comments, 2 participants]