can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro / Mac mini M5 Pro (48GB) run Gemma 3 12B?

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

Yes — it runs great.

Best fit: Gemma 3 12B at Q8_0 · 12.5 GB · 14–22 tok/s on a MacBook Pro / Mac mini M5 Pro (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.8 GB31–47 tok/sRuns great
Q3_K_M6.0 GB26–40 tok/sRuns great
Q4_K_M7.3 GB23–34 tok/sRuns great
Q5_K_M8.5 GB20–30 tok/sRuns great
Q6_K9.7 GB18–27 tok/sRuns great
Q8_012.5 GB14–22 tok/sRuns great
FP1623.5 GB8–12 tok/sTight / slow

Ran Gemma 3 12B on a MacBook Pro / Mac mini M5 Pro (48GB)? Add your real numbers →