can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (18GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 18.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q5_K_M · 6.3 GB · 13–20 tok/s on a MacBook Pro M3 Pro (18GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB22–32 tok/sRuns great
Q3_K_M4.4 GB18–27 tok/sRuns great
Q4_K_M5.4 GB15–23 tok/sRuns great
Q5_K_M6.3 GB13–20 tok/sRuns great
Q6_K7.2 GB12–18 tok/sTight / slow
Q8_09.4 GB10–14 tok/sTight / slow
FP1617.6 GB5–8 tok/sWon't fit

Ran Granite 4.2 8B on a MacBook Pro M3 Pro (18GB)? Add your real numbers →