can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at Q5_K_M · 1.9 GB · 13–19 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB19–29 tok/sRuns great
Q3_K_M1.2 GB17–26 tok/sRuns great
Q4_K_M1.6 GB14–21 tok/sRuns great
Q5_K_M1.9 GB13–19 tok/sRuns great
Q6_K2.1 GB12–18 tok/sTight / slow
Q8_02.7 GB10–15 tok/sTight / slow
FP165.0 GB6–9 tok/sTight / slow

Ran MiniCPM5 2B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →