can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (24GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q8_0 · 9.4 GB · 18–28 tok/s on a MacBook Pro M5 Pro (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB39–59 tok/sRuns great
Q3_K_M4.4 GB33–50 tok/sRuns great
Q4_K_M5.4 GB29–43 tok/sRuns great
Q5_K_M6.3 GB25–38 tok/sRuns great
Q6_K7.2 GB23–34 tok/sRuns great
Q8_09.4 GB18–28 tok/sRuns great
FP1617.6 GB11–16 tok/sWon't fit

Ran Granite 4.2 8B on a MacBook Pro M5 Pro (24GB)? Add your real numbers →