Compatibility check
Can I run Lite Whisper Large v3 Acc on Apple M4 Max (32-core GPU)?
Yes — it runs.best quant:
Decode speed
338 tok/sest
Usable context
262K
Memory
64 GB
Fits in memory338 tok/sest · 262K ctx
Fits in memory288 tok/sest · 262K ctx
Fits in memory193 tok/sest · 262K ctx