can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Max (128GB) run Gemma 3 27B?

Gemma · Gemma · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 3 27B at Q6_K · 22.2 GB · 14–21 tok/s on a MacBook Pro M4 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB25–38 tok/sRuns great
Q3_K_M13.4 GB21–31 tok/sRuns great
Q4_K_M16.6 GB18–27 tok/sRuns great
Q5_K_M19.3 GB16–24 tok/sRuns great
Q6_K22.2 GB14–21 tok/sRuns great
Q8_028.7 GB11–17 tok/sTight / slow
FP1654.0 GB6–9 tok/sTight / slow

Ran Gemma 3 27B on a MacBook Pro M4 Max (128GB)? Add your real numbers →