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

Compatibility check

Can I run Llama 3.2 1B Instruct on GeForce RTX 4060 8GB?

Yes — it runs.best quant:

Decode speed

299 tok/sest

Usable context

33K

Memory

8 GB

Fits in memory299 tok/sest · 33K ctx

Fits in memory255 tok/sest · 33K ctx

Fits in memory171 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

GeForce RTX 4060 8GB

8 GB · everything it runs →