Compatibility check
Can I run Qwen3 ASR 0.6B HF on Apple M2 Max (38-core GPU)?
Yes — it runs.best quant:
Decode speed
577 tok/sest
Usable context
262K
Memory
96 GB
Fits in memory577 tok/sest · 262K ctx
Fits in memory492 tok/sest · 262K ctx
Fits in memory329 tok/sest · 262K ctx