Ollama on an AMD GPU: Five Failures That Drop You to CPU Without Telling You
This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.
The worst Ollama failure on an AMD GPU isn't the one that takes your server down. It's the one that takes nothing down: Ollama starts, responds, answers correctly — and does it on CPU, at 15.89 tokens per second instead of 132.48. An 8.3x penalty that shows up in no log unless you go looking, becau…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-28 10:22 · DEV Community — AI
Ollama on an AMD GPU: Five Failures That Drop You to CPU Without Telling You