Models /Granite Speech 4.1 2b NAR /Can I run it?

Compatibility check

Can I run Granite Speech 4.1 2b NAR on Apple M2 (8-core GPU, 8GB unified)?

Yes — it runs.best quant:

Decode speed

50 tok/sest

Usable context

33K

Memory

8 GB

Fits in memory50 tok/sest · 33K ctx

Fits in memory43 tok/sest · 33K ctx

Fits in memory29 tok/sest · 16K ctx

What is quantisation? →

Granite Speech 4.1 2b NAR

2.3B · full specs & benchmarks →

Apple M2 (8-core GPU, 8GB unified)

8 GB · everything it runs →