Models /Granite Speech 3.3 2b /Can I run it?

Compatibility check

Can I run Granite Speech 3.3 2b on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant:

Decode speed

236 tok/sest

Usable context

262K

Memory

128 GB

Fits in memory236 tok/sest · 262K ctx

Fits in memory201 tok/sest · 262K ctx

Fits in memory135 tok/sest · 262K ctx

What is quantisation? →

Granite Speech 3.3 2b

3B · full specs & benchmarks →

Apple M5 Max (40-core GPU)

128 GB · everything it runs →