can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Granite 4.2 30B?

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

Yes — it runs great.

Best fit: Granite 4.2 30B at Q5_K_M · 20.8 GB · 13–20 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB23–34 tok/sRuns great
Q3_K_M14.1 GB18–27 tok/sRuns great
Q4_K_M17.7 GB15–23 tok/sRuns great
Q5_K_M20.8 GB13–20 tok/sRuns great
Q6_K24.0 GB12–17 tok/sWon't fit
Q8_031.1 GB9–14 tok/sWon't fit
FP1658.6 GB5–8 tok/sWon't fit

Ran Granite 4.2 30B on a MacBook Pro M5 Max (36GB)? Add your real numbers →