Can I run it?
Can I run Qwen2.5 32B Instruct on Apple M3 Pro?
Tight fit
Tight fit fully in unified memory on your Apple M3 Pro at IQ2_S, 8K context, about 6.6–9.0 tok/s. Weights 9.67 GB plus 2.00 GB of KV cache — 12.1 GB of 13.0 GB usable.
Best quantIQ2_S
Working context8K
Max that fits8K
Speed6.6–9.0 tok/s
Weights9.67 GB
KV cache2.00 GB
Total12.1 GB
Usable13.0 GB
Qwen2.5 32B Instruct details · Apple M3 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Qwen2.5-32B-Instruct-GGUF:IQ2_S -c 8192 -ngl 64
Ollama
ollama run qwen2.5
LM Studio
lms get bartowski/Qwen2.5-32B-Instruct-GGUF # Then load quant IQ2_S
Assumptions
- Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- IQ2_S size is the real GGUF file size from Hugging Face.
- Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on Apple M3 Pro? — Tight fit, UD-Q2_K_XL, 67–91 tok/s
- Can I run Qwen3.5 35B A3B on Apple M3 Pro? — Tight fit, UD-IQ3_XXS, 68–93 tok/s
Updated 2026-10-24. Profile on this page is the device default.