can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M2 (16GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q3_K_M · 4.4 GB · 12–19 tok/s on a MacBook Air/Pro M2 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB15–23 tok/sRuns great
Q3_K_M4.4 GB12–19 tok/sRuns great
Q4_K_M5.4 GB11–16 tok/sTight / slow
Q5_K_M6.3 GB9–14 tok/sTight / slow
Q6_K7.2 GB8–12 tok/sTight / slow
Q8_09.4 GB6–10 tok/sTight / slow
FP1617.6 GB4–5 tok/sWon't fit

Ran Granite 4.2 8B on a MacBook Air/Pro M2 (16GB)? Add your real numbers →