Compatibility check
Can I run Qwen3 VL 8B Thinking on Apple M2 Max (38-core GPU)?
Yes — it runs.best quant:
Decode speed
53 tok/sest
Usable context
131K
Memory
96 GB
Fits in memory53 tok/sest · 131K ctx
Fits in memory45 tok/sest · 131K ctx
Fits in memory30 tok/sest · 131K ctx