can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (24GB) run Gemma 4 E4B?

Gemma · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 E4B at Q8_0 · 8.2 GB · 33–50 tok/s on a MacBook Pro M5 Pro (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.1 GB55–82 tok/sRuns great
Q4_K_M5.0 GB48–72 tok/sRuns great
Q5_K_M5.5 GB45–67 tok/sRuns great
Q6_K7.1 GB37–56 tok/sRuns great
Q8_08.2 GB33–50 tok/sRuns great
FP1615.1 GB20–30 tok/sTight / slow

Ran Gemma 4 E4B on a MacBook Pro M5 Pro (24GB)? Add your real numbers →