can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (128GB) run Gemma 3 12B?

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

Yes — it runs great.

Best fit: Gemma 3 12B at FP16 · 23.5 GB · 15–23 tok/s on a MacBook Pro M5 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB47–71 tok/sRuns great
Q3_K_M6.0 GB41–62 tok/sRuns great
Q4_K_M7.3 GB37–55 tok/sRuns great
Q5_K_M8.5 GB33–50 tok/sRuns great
Q6_K9.7 GB30–45 tok/sRuns great
Q8_012.5 GB25–38 tok/sRuns great
FP1623.5 GB15–23 tok/sRuns great

Ran Gemma 3 12B on a MacBook Pro M5 Max (128GB)? Add your real numbers →