can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (128GB) run Gemma 4 E4B?

Gemma · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 E4B at FP16 · 15.1 GB · 44–66 tok/s on a Mac Studio M1 Ultra (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.1 GB94–141 tok/sRuns great
Q4_K_M5.0 GB86–129 tok/sRuns great
Q5_K_M5.5 GB82–123 tok/sRuns great
Q6_K7.1 GB72–108 tok/sRuns great
Q8_08.2 GB66–99 tok/sRuns great
FP1615.1 GB44–66 tok/sRuns great

Ran Gemma 4 E4B on a Mac Studio M1 Ultra (128GB)? Add your real numbers →