can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (16GB) run Gemma 4 12B?

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

Yes — it runs great.

Best fit: Gemma 4 12B at Q4_K_M · 7.1 GB · 13–19 tok/s on a MacBook Air/Pro M5 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.7 GB15–23 tok/sRuns great
Q4_K_M7.1 GB13–19 tok/sRuns great
Q5_K_M8.4 GB11–16 tok/sTight / slow
Q6_K9.8 GB10–14 tok/sTight / slow
Q8_012.7 GB8–11 tok/sWon't fit
FP1623.8 GB4–6 tok/sWon't fit

Ran Gemma 4 12B on a MacBook Air/Pro M5 (16GB)? Add your real numbers →