Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on Apple M2 Max (38-core GPU)?
Yes — it runs.best quant:
Decode speed
14 tok/sest
Usable context
33K
Memory
96 GB
Fits in memory14 tok/sest · 33K ctx
Fits in memory12 tok/sest · 33K ctx
Fits in memory8 tok/sest · 33K ctx