can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Max (64GB) run Granite 4.2 30B?

Granite · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 30B at Q4_K_M · 17.7 GB · 13–20 tok/s on a MacBook Pro M3 Max (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB20–30 tok/sRuns great
Q3_K_M14.1 GB16–24 tok/sRuns great
Q4_K_M17.7 GB13–20 tok/sRuns great
Q5_K_M20.8 GB12–17 tok/sTight / slow
Q6_K24.0 GB10–15 tok/sTight / slow
Q8_031.1 GB8–12 tok/sTight / slow
FP1658.6 GB4–7 tok/sWon't fit

Ran Granite 4.2 30B on a MacBook Pro M3 Max (64GB)? Add your real numbers →