Compatibility check
Can I run Qwen2.5 Coder 32B Instruct on Apple M1 Ultra (64-core GPU)?
Yes — it runs.best quant:
Decode speed
28 tok/sest
Usable context
33K
Memory
128 GB
Fits in memory28 tok/sest · 33K ctx
Fits in memory24 tok/sest · 33K ctx
Fits in memory16 tok/sest · 33K ctx