can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 12B at Q8_0 · 12.7 GB · 21–31 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M5.7 GB39–59 tok/sRuns great
Q4_K_M7.1 GB33–50 tok/sRuns great
Q5_K_M8.4 GB29–44 tok/sRuns great
Q6_K9.8 GB26–39 tok/sRuns great
Q8_012.7 GB21–31 tok/sRuns great
FP1623.8 GB12–18 tok/sTight / slow

Ran Gemma 4 12B on a MacBook Pro M5 Max (36GB)? Add your real numbers →