Models /Llama 3.2 1B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.2 1B Instruct on Radeon RX 7900 XT?

Yes — it runs.best quant:

Decode speed

715 tok/sest

Usable context

33K

Memory

20 GB

Fits in memory715 tok/sest · 33K ctx

Fits in memory609 tok/sest · 33K ctx

Fits in memory408 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

Radeon RX 7900 XT

20 GB · everything it runs →