can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (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 Q8_0 · 31.1 GB · 15–23 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB36–54 tok/sRuns great
Q3_K_M14.1 GB29–44 tok/sRuns great
Q4_K_M17.7 GB25–37 tok/sRuns great
Q5_K_M20.8 GB22–32 tok/sRuns great
Q6_K24.0 GB19–29 tok/sRuns great
Q8_031.1 GB15–23 tok/sRuns great
FP1658.6 GB9–13 tok/sWon't fit

Ran Granite 4.2 30B on a Mac Studio M1 Ultra (64GB)? Add your real numbers →