can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M4 Max (48GB) run Gemma 4 E4B?

Gemma · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 E4B at FP16 · 15.1 GB · 33–49 tok/s on a MacBook Pro M4 Max (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.1 GB78–117 tok/sRuns great
Q4_K_M5.0 GB70–105 tok/sRuns great
Q5_K_M5.5 GB66–99 tok/sRuns great
Q6_K7.1 GB56–85 tok/sRuns great
Q8_08.2 GB51–77 tok/sRuns great
FP1615.1 GB33–49 tok/sRuns great

Ran Gemma 4 E4B on a MacBook Pro M4 Max (48GB)? Add your real numbers →