can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M1 (16GB) run Gemma 3 12B?

Gemma · Gemma · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Gemma 3 12B at Q2_K · 4.8 GB · 7–10 tok/s on a MacBook Air/Pro M1 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB7–10 tok/sTight / slow
Q3_K_M6.0 GB6–9 tok/sTight / slow
Q4_K_M7.3 GB5–7 tok/sTight / slow
Q5_K_M8.5 GB4–7 tok/sTight / slow
Q6_K9.7 GB4–6 tok/sWon't fit
Q8_012.5 GB3–5 tok/sWon't fit
FP1623.5 GB2–3 tok/sWon't fit

Ran Gemma 3 12B on a MacBook Air/Pro M1 (16GB)? Add your real numbers →