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

Compatibility check

Can I run Granite Speech 4.1 2b NAR on GeForce RTX 3090?

Yes — it runs.best quant:

Decode speed

537 tok/sest

Usable context

131K

Memory

24 GB

Fits in memory537 tok/sest · 131K ctx

Fits in memory458 tok/sest · 131K ctx

Fits in memory306 tok/sest · 131K ctx

What is quantisation? →

Granite Speech 4.1 2b NAR

2.3B · full specs & benchmarks →

GeForce RTX 3090

24 GB · everything it runs →