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

Compatibility check

Can I run Granite Speech 4.1 2b NAR on Instinct MI300X?

Yes — it runs.best quant:

Decode speed

2471 tok/sest

Usable context

262K

Memory

192 GB

Fits in memory2471 tok/sest · 262K ctx

Fits in memory2106 tok/sest · 262K ctx

Fits in memory1410 tok/sest · 262K ctx

What is quantisation? →

Granite Speech 4.1 2b NAR

2.3B · full specs & benchmarks →

Instinct MI300X

192 GB · everything it runs →