can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Pro (48GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 12B at Q6_K · 9.8 GB · 13–20 tok/s on a MacBook Pro M4 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.1 GB21–31 tok/sRuns great
Q4_K_M7.2 GB17–25 tok/sRuns great
Q5_K_M8.5 GB15–22 tok/sRuns great
Q6_K9.8 GB13–20 tok/sRuns great
Q8_012.7 GB11–17 tok/sTight / slow
FP1623.8 GB7–10 tok/sTight / slow

Ran Gemma 4 12B on a MacBook Pro M4 Pro (48GB)? Add your real numbers →