can-i-run-this-llm

Can I run this LLM?

Can a Mac mini M6 (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 · 19–29 tok/s on a Mac mini M6 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K1.0 GB62–93 tok/sRuns great
Q3_K_M1.2 GB55–83 tok/sRuns great
Q4_K_M1.6 GB47–70 tok/sRuns great
Q5_K_M1.9 GB41–62 tok/sRuns great
Q6_K2.1 GB39–58 tok/sRuns great
Q8_02.7 GB33–49 tok/sRuns great
FP165.0 GB19–29 tok/sRuns great

Ran MiniCPM5 2B on a Mac mini M6 (24GB)? Add your real numbers →