Can I run it?
Can I run Qwen2.5 32B Instruct on Apple M5 Max (40-core GPU)?
Tight fit
Tight fit fully in unified memory on your Apple M5 Max (40-core GPU) at Q8_0, 8K context, about 9.1–12 tok/s. Weights 32.4 GB plus 2.00 GB of KV cache — 35.1 GB of 36.0 GB usable.
Best quantQ8_0
Working context8K
Max that fits8K
Speed9.1–12 tok/s
Weights32.4 GB
KV cache2.00 GB
Total35.1 GB
Usable36.0 GB
Qwen2.5 32B Instruct details · Apple M5 Max (40-core GPU) page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Qwen2.5-32B-Instruct-GGUF:Q8_0 -c 8192 -ngl 64
Ollama
ollama run qwen2.5
LM Studio
lms get bartowski/Qwen2.5-32B-Instruct-GGUF # Then load quant Q8_0
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%.
- Q8_0 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 M5 Max (40-core GPU)? — Tight fit, Q8_0, 100–137 tok/s
- Can I run Qwen3.8 35B A3B Distill on Apple M5 Max (40-core GPU)? — Runs, Q6_K, 128–175 tok/s
- Can I run Qwen3.5 35B A3B on Apple M5 Max (40-core GPU)? — Tight fit, Q8_0, 100–137 tok/s
Updated 2026-10-24. Profile on this page is the device default.