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

Compatibility check

Can I run Llama 3.2 3B Instruct on GeForce RTX 5070?

Yes — it runs.best quant:

Decode speed

277 tok/sest

Usable context

131K

Memory

12 GB

Fits in memory277 tok/sest · 131K ctx

Fits in memory236 tok/sest · 131K ctx

Fits in memory158 tok/sest · 131K ctx

What is quantisation? →

Llama 3.2 3B Instruct

3.2B · full specs & benchmarks →

GeForce RTX 5070

12 GB · everything it runs →