can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M1 (8GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 8.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Granite 4.2 8B at Q2_K · 3.4 GB · 11–16 tok/s on a MacBook Air M1 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB11–16 tok/sTight / slow
Q3_K_M4.4 GB9–13 tok/sWon't fit
Q4_K_M5.4 GB7–11 tok/sWon't fit
Q5_K_M6.3 GB6–10 tok/sWon't fit
Q6_K7.2 GB6–8 tok/sWon't fit
Q8_09.4 GB4–7 tok/sWon't fit
FP1617.6 GB2–4 tok/sWon't fit

Ran Granite 4.2 8B on a MacBook Air M1 (8GB)? Add your real numbers →