Models /Voxtral Mini 4B Realtime 2602 /Can I run it?

Compatibility check

Can I run Voxtral Mini 4B Realtime 2602 on Apple M2 Max (38-core GPU)?

Yes — it runs.best quant:

Decode speed

105 tok/sest

Usable context

262K

Memory

96 GB

Fits in memory105 tok/sest · 262K ctx

Fits in memory90 tok/sest · 262K ctx

Fits in memory60 tok/sest · 262K ctx

What is quantisation? →

Voxtral Mini 4B Realtime 2602

4.4B · full specs & benchmarks →

Apple M2 Max (38-core GPU)

96 GB · everything it runs →