Compatibility check
Can I run Qwen2.5 VL 72B Instruct on Apple M2 Ultra (76-core GPU)?
Yes — it runs.best quant:
Decode speed
13 tok/sest
Usable context
66K
Memory
192 GB
Fits in memory13 tok/sest · 66K ctx
Fits in memory11 tok/sest · 66K ctx
Fits in memory7 tok/sest · 66K ctx