can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M2 Max (96GB) run Gemma 3 27B?

Gemma · Gemma · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 3 27B at Q4_K_M · 16.6 GB · 13–20 tok/s on a MacBook Pro M2 Max (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB19–29 tok/sRuns great
Q3_K_M13.4 GB16–24 tok/sRuns great
Q4_K_M16.6 GB13–20 tok/sRuns great
Q5_K_M19.3 GB12–18 tok/sTight / slow
Q6_K22.2 GB10–16 tok/sTight / slow
Q8_028.7 GB8–13 tok/sTight / slow
FP1654.0 GB5–7 tok/sTight / slow

Ran Gemma 3 27B on a MacBook Pro M2 Max (96GB)? Add your real numbers →