can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (256GB) run Gemma 3 27B?

Gemma · Gemma · estimated for a 256.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 3 27B at FP16 · 54.0 GB · 14–21 tok/s on a Mac Studio M5 Ultra (256GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB51–77 tok/sRuns great
Q3_K_M13.4 GB44–65 tok/sRuns great
Q4_K_M16.6 GB37–56 tok/sRuns great
Q5_K_M19.3 GB33–50 tok/sRuns great
Q6_K22.2 GB30–45 tok/sRuns great
Q8_028.7 GB24–36 tok/sRuns great
FP1654.0 GB14–21 tok/sRuns great

Ran Gemma 3 27B on a Mac Studio M5 Ultra (256GB)? Add your real numbers →