can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at FP16 · 5.0 GB · 103–154 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB232–347 tok/sRuns great
Q3_K_M1.2 GB216–324 tok/sRuns great
Q4_K_M1.6 GB195–292 tok/sRuns great
Q5_K_M1.9 GB180–271 tok/sRuns great
Q6_K2.1 GB173–259 tok/sRuns great
Q8_02.7 GB152–229 tok/sRuns great
FP165.0 GB103–154 tok/sRuns great
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsMiniCPM5 2B on other machinesWhat to buy to run it →

Ran MiniCPM5 2B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →