Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on Apple M5 Max (32-core GPU)?
Yes — it runs.best quant:
Decode speed
16 tok/sest
Usable context
33K
Memory
64 GB
Fits in memory16 tok/sest · 33K ctx
Fits in memory14 tok/sest · 33K ctx
Fits in memory9 tok/sest · 33K ctx