can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Mistral Small 3.2 24B?

Mistral · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Mistral Small 3.2 24B at Q6_K · 19.4 GB · 14–21 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K8.9 GB27–41 tok/sRuns great
Q3_K_M11.5 GB22–33 tok/sRuns great
Q4_K_M14.3 GB18–28 tok/sRuns great
Q5_K_M16.8 GB16–24 tok/sRuns great
Q6_K19.4 GB14–21 tok/sRuns great
Q8_025.1 GB11–17 tok/sWon't fit
FP1647.2 GB6–9 tok/sWon't fit

Ran Mistral Small 3.2 24B on a MacBook Pro M5 Max (36GB)? Add your real numbers →