can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Gemma 4 E4B?

Gemma · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Gemma 4 E4B at Q3_K_M · 4.1 GB · 11–16 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M4.1 GB11–16 tok/sTight / slow
Q4_K_M5.0 GB9–13 tok/sTight / slow
Q5_K_M5.5 GB8–12 tok/sTight / slow
Q6_K7.1 GB7–10 tok/sTight / slow
Q8_08.2 GB6–9 tok/sTight / slow
FP1615.1 GB3–5 tok/sTight / slow

Ran Gemma 4 E4B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →