can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Gemma 4 26B-A4B (MoE)?

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

Yes, but it's tight.

Best fit: Gemma 4 26B-A4B (MoE) at Q3_K_M · 12.7 GB · 12–17 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M12.7 GB12–17 tok/sTight / slow
Q4_K_M17.0 GB9–14 tok/sTight / slow
Q5_K_M21.2 GB8–12 tok/sTight / slow
Q6_K23.2 GB7–11 tok/sTight / slow
Q8_026.9 GB6–10 tok/sWon't fit
FP1650.5 GB4–6 tok/sWon't fit

Ran Gemma 4 26B-A4B (MoE) on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →