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

Compatibility check

Can I run Llama 3.2 3B Instruct on GeForce RTX 3060 8GB?

Yes — it runs.best quant:

Decode speed

149 tok/sest

Usable context

66K

Memory

8 GB

Fits in memory149 tok/sest · 66K ctx

Fits in memory127 tok/sest · 66K ctx

Fits in memory85 tok/sest · 66K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

GeForce RTX 3060 8GB

8 GB · everything it runs →