Models /Whisper Large v3 /Can I run it?

Compatibility check

Can I run Whisper Large v3 on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:

Decode speed

630 tok/sest

Usable context

262K

Memory

512 GB

Fits in memory630 tok/sest · 262K ctx

Fits in memory537 tok/sest · 262K ctx

Fits in memory360 tok/sest · 262K ctx

What is quantisation? →

Whisper Large v3

1.5B · full specs & benchmarks →

Apple M3 Ultra (80-core GPU)

512 GB · everything it runs →