can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at FP16 · 5.0 GB · 162–242 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB285–427 tok/sRuns great
Q3_K_M1.2 GB273–409 tok/sRuns great
Q4_K_M1.6 GB255–383 tok/sRuns great
Q5_K_M1.9 GB243–364 tok/sRuns great
Q6_K2.1 GB236–353 tok/sRuns great
Q8_02.7 GB216–325 tok/sRuns great
FP165.0 GB162–242 tok/sRuns great

Ran MiniCPM5 2B on a NVIDIA A100 (80GB)? Add your real numbers →