can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Llama 3.2 1B?

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

Yes — it runs great.

Best fit: Llama 3.2 1B at Q8_0 · 1.3 GB · 17–25 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.8 GB24–35 tok/sRuns great
Q5_K_M0.9 GB22–32 tok/sRuns great
Q6_K1.0 GB20–30 tok/sRuns great
Q8_01.3 GB17–25 tok/sRuns great
FP162.5 GB10–16 tok/sTight / slow

Ran Llama 3.2 1B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →