Can I run it?
Can I run Qwen2.5 32B Instruct on Apple M5?
Tight fit
Tight fit fully in unified memory on your Apple M5 at IQ2_XXS, 4K context, about 8.3–11 tok/s. Weights 8.41 GB plus 1.00 GB of KV cache — 9.79 GB of 11.0 GB usable.
Best quantIQ2_XXS
Working context4K
Max that fits4K
Speed8.3–11 tok/s
Weights8.41 GB
KV cache1.00 GB
Total9.79 GB
Usable11.0 GB
Qwen2.5 32B Instruct details · Apple M5 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Qwen2.5-32B-Instruct-GGUF:IQ2_XXS -c 4096 -ngl 64
Ollama
ollama run qwen2.5
LM Studio
lms get bartowski/Qwen2.5-32B-Instruct-GGUF # Then load quant IQ2_XXS
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_XXS 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 4K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on Apple M5? — Tight fit, UD-IQ2_XXS, 77–104 tok/s
- Can I run Qwen3.5 35B A3B on Apple M5? — Tight fit, UD-IQ2_XXS, 77–105 tok/s
Updated 2026-10-24. Profile on this page is the device default.