can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3050 Laptop (6GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 6.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at Q8_0 · 2.7 GB · 39–58 tok/s on a NVIDIA RTX 3050 Laptop (6GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB81–122 tok/sRuns great
Q3_K_M1.2 GB71–106 tok/sRuns great
Q4_K_M1.6 GB58–87 tok/sRuns great
Q5_K_M1.9 GB51–76 tok/sRuns great
Q6_K2.1 GB47–71 tok/sRuns great
Q8_02.7 GB39–58 tok/sRuns great
FP165.0 GB22–34 tok/sWon't fit

Ran MiniCPM5 2B on a NVIDIA RTX 3050 Laptop (6GB)? Add your real numbers →