can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Llama 3.2 3B?

Llama · Llama 3.2 Community · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Llama 3.2 3B at Q4_K_M · 1.9 GB · 11–17 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.9 GB11–17 tok/sTight / slow
Q5_K_M2.3 GB10–15 tok/sTight / slow
Q6_K2.6 GB9–13 tok/sTight / slow
Q8_03.4 GB7–11 tok/sTight / slow
FP166.4 GB4–7 tok/sTight / slow

Ran Llama 3.2 3B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →