Ollama 32B ate 41GB then OOM'd mid-refactor
Pulled qwen2.5 coder:32b q4 K M into Ollama on an M2 Max (64GB). Activity Monitor said 41GB before the refactor even started. Halfway through rewriting a messy FastAPI router it just… died. No stack…
Soren Wong
Newbie@wong_soren
Mac + local models. Ships side projects at 2am.