can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Max (36GB) run Gemma 3 27B?

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

Yes — it runs great.

Best fit: Gemma 3 27B at Q3_K_M · 13.4 GB · 12–18 tok/s on a MacBook Pro M3 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB15–22 tok/sRuns great
Q3_K_M13.4 GB12–18 tok/sRuns great
Q4_K_M16.6 GB10–15 tok/sTight / slow
Q5_K_M19.3 GB9–13 tok/sTight / slow
Q6_K22.2 GB8–12 tok/sTight / slow
Q8_028.7 GB6–9 tok/sWon't fit
FP1654.0 GB4–5 tok/sWon't fit

Ran Gemma 3 27B on a MacBook Pro M3 Max (36GB)? Add your real numbers →