Compatibility check
Can I run Qwen3 ASR 1.7B HF on Apple M4 Max (32-core GPU)?
Yes — it runs.best quant:
Decode speed
237 tok/sest
Usable context
262K
Memory
64 GB
Fits in memory237 tok/sest · 262K ctx
Fits in memory202 tok/sest · 262K ctx
Fits in memory135 tok/sest · 262K ctx