Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on Apple M4 Pro (20-core GPU)?
Yes — it runs.best quant:
Decode speed
10 tok/sest
Usable context
33K
Memory
64 GB
Fits in memory10 tok/sest · 33K ctx
Fits in memory8 tok/sest · 33K ctx
Fits in memory6 tok/sest · 33K ctx