can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M1 Pro (32GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiniCPM5 2B at FP16 · 5.0 GB · 22–34 tok/s on a MacBook Pro M1 Pro (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB68–103 tok/sRuns great
Q3_K_M1.2 GB61–92 tok/sRuns great
Q4_K_M1.6 GB52–78 tok/sRuns great
Q5_K_M1.9 GB47–70 tok/sRuns great
Q6_K2.1 GB44–66 tok/sRuns great
Q8_02.7 GB37–56 tok/sRuns great
FP165.0 GB22–34 tok/sRuns great

Ran MiniCPM5 2B on a MacBook Pro M1 Pro (32GB)? Add your real numbers →