can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5080 (16GB) run Gemma 4 26B-A4B (MoE)?

Gemma · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Gemma 4 26B-A4B (MoE) at Q3_K_M · 12.7 GB · 167–251 tok/s on a NVIDIA RTX 5080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M12.7 GB167–251 tok/sTight / slow
Q4_K_M17.0 GB144–217 tok/sWon't fit
Q5_K_M21.2 GB127–191 tok/sWon't fit
Q6_K23.2 GB120–180 tok/sWon't fit
Q8_026.9 GB109–164 tok/sWon't fit
FP1650.5 GB69–104 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 5080 (16GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →

Ran Gemma 4 26B-A4B (MoE) on a NVIDIA RTX 5080 (16GB)? Add your real numbers →