Compatibility check
Can I run Qwen3 ASR 0.6B on Apple M2 Ultra (76-core GPU)?
Yes — it runs.best quant:
Decode speed
1026 tok/sest
Usable context
262K
Memory
192 GB
Fits in memory1026 tok/sest · 262K ctx
Fits in memory875 tok/sest · 262K ctx
Fits in memory586 tok/sest · 262K ctx