can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run Gemma 4 26B-A4B (MoE)?

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

Yes — it runs great.

Best fit: Gemma 4 26B-A4B (MoE) at Q4_K_M · 15.3 GB · 120–180 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M10.9 GB135–202 tok/sRuns great
Q4_K_M15.3 GB120–180 tok/sRuns great
Q5_K_M18.0 GB112–168 tok/sTight / slow
Q6_K20.8 GB105–157 tok/sWon't fit
Q8_026.8 GB93–139 tok/sWon't fit
FP1650.5 GB63–95 tok/sWon't fit

Ran Gemma 4 26B-A4B (MoE) on a NVIDIA RTX 4090 (24GB)? Add your real numbers →