Can I run QwQ-32B on a Mac with 32 GB?
Yes, with a GGUF version
The published weights are too big, but the Q4_K_M file from Qwen/QwQ-32B-GGUF (19.9 GB) fits, with room for ≈ 6K tokens of context.
ollama run hf.co/Qwen/QwQ-32B-GGUF:Q4_K_MFiles and context on Mac with 32 GB
Each file of QwQ-32B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On Mac with 32 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 65.5 GB | Doesn't fit | — | — |
| qwq-32b-fp16 | 65.5 GB | Doesn't fit | — | — |
| Q8_0 | 34.8 GB | Doesn't fit | — | — |
| Q6_K | 26.9 GB | Doesn't fit | — | — |
| Q5_K_M | 23.3 GB | Doesn't fit | — | — |
| Q5_0 | 22.6 GB | Doesn't fit | — | — |
| Q4_K_M | 19.9 GB | Tight | 6K | 11K |