Models /Granite 4.0 Micro /Can I run it?

Compatibility check

Can I run Granite 4.0 Micro on RTX 6000 Ada?

Yes — it runs.best quant:

Decode speed

396 tok/sest

Usable context

66K

Memory

48 GB

Fits in memory396 tok/sest · 66K ctx

Fits in memory337 tok/sest · 66K ctx

Fits in memory226 tok/sest · 66K ctx

What is quantisation? →

Granite 4.0 Micro

3.2B · full specs & benchmarks →

48 GB · everything it runs →