Compatibility check
Can I run Qwen3.5-9B on Apple M3 Pro (18-core GPU)?
Yes — it runs.best quant:
Decode speed
18 tok/sest
Usable context
131K
Memory
36 GB
Fits in memory18 tok/sest · 131K ctx
Fits in memory15 tok/sest · 131K ctx
Fits in memory10 tok/sest · 66K ctx