can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at FP16 · 5.0 GB · 92–138 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB218–327 tok/sRuns great
Q3_K_M1.2 GB202–303 tok/sRuns great
Q4_K_M1.6 GB180–271 tok/sRuns great
Q5_K_M1.9 GB166–250 tok/sRuns great
Q6_K2.1 GB159–238 tok/sRuns great
Q8_02.7 GB139–208 tok/sRuns great
FP165.0 GB92–138 tok/sRuns great

Ran MiniCPM5 2B on a NVIDIA L40S (48GB)? Add your real numbers →