can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run Granite 4.2 30B?

Granite · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 30B at Q6_K · 24.0 GB · 15–23 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB29–43 tok/sRuns great
Q3_K_M14.1 GB24–35 tok/sRuns great
Q4_K_M17.7 GB20–29 tok/sRuns great
Q5_K_M20.8 GB17–26 tok/sRuns great
Q6_K24.0 GB15–23 tok/sRuns great
Q8_031.1 GB12–18 tok/sTight / slow
FP1658.6 GB7–10 tok/sTight / slow

Ran Granite 4.2 30B on a MacBook Pro M5 Max (128GB)? Add your real numbers →