Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on Apple M5 Max (40-core GPU)?
Yes — it runs.best quant:
Decode speed
22 tok/sest
Usable context
33K
Memory
128 GB
Fits in memory22 tok/sest · 33K ctx
Fits in memory18 tok/sest · 33K ctx
Fits in memory12 tok/sest · 33K ctx