Models /Voxtral Small 24B 2507 /Can I run it?

Compatibility check

Can I run Voxtral Small 24B 2507 on Apple M2 Ultra (76-core GPU)?

Yes — it runs.best quant:

Decode speed

38 tok/sest

Usable context

16K

Memory

192 GB

Fits in memory38 tok/sest · 16K ctx

Fits in memory32 tok/sest · 16K ctx

Fits in memory22 tok/sest · 16K ctx

What is quantisation? →

Voxtral Small 24B 2507

24.3B · full specs & benchmarks →

Apple M2 Ultra (76-core GPU)

192 GB · everything it runs →