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

Compatibility check

Can I run Llama 3.2 1B Instruct on GeForce GTX 1660 SUPER?

Yes — it runs.best quant:

Decode speed

370 tok/sest

Usable context

33K

Memory

6 GB

Fits in memory370 tok/sest · 33K ctx

Fits in memory315 tok/sest · 33K ctx

Fits in memory211 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

GeForce GTX 1660 SUPER

6 GB · everything it runs →