Models /Llama 3.2 3B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 3B Instruct on RTX PRO 6000 Blackwell?

Yes — it runs.best quant:

Decode speed

739 tok/sest

Usable context

131K

Memory

96 GB

Fits in memory739 tok/sest · 131K ctx

Fits in memory630 tok/sest · 131K ctx

Fits in memory422 tok/sest · 131K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

RTX PRO 6000 Blackwell

96 GB · everything it runs →