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

Compatibility check

Can I run Llama 3.2 1B Instruct on Radeon RX 9070 XT?

Yes — it runs.best quant:

Decode speed

572 tok/sest

Usable context

33K

Memory

16 GB

Fits in memory572 tok/sest · 33K ctx

Fits in memory487 tok/sest · 33K ctx

Fits in memory326 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

Radeon RX 9070 XT

16 GB · everything it runs →