can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M1 (16GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at Q8_0 · 2.7 GB · 15–22 tok/s on a MacBook Air/Pro M1 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB32–47 tok/sRuns great
Q3_K_M1.2 GB27–41 tok/sRuns great
Q4_K_M1.6 GB22–33 tok/sRuns great
Q5_K_M1.9 GB19–29 tok/sRuns great
Q6_K2.1 GB18–27 tok/sRuns great
Q8_02.7 GB15–22 tok/sRuns great
FP165.0 GB8–13 tok/sTight / slow

Ran MiniCPM5 2B on a MacBook Air/Pro M1 (16GB)? Add your real numbers →