Can I run this LLM?
Can a NVIDIA RTX 4080 (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 · 141–212 tok/s on a NVIDIA RTX 4080 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 12.7 GB | 141–212 tok/s | Tight / slow |
| Q4_K_M | 17.0 GB | 120–180 tok/s | Won't fit |
| Q5_K_M | 21.2 GB | 104–156 tok/s | Won't fit |
| Q6_K | 23.2 GB | 98–147 tok/s | Won't fit |
| Q8_0 | 26.9 GB | 88–133 tok/s | Won't fit |
| FP16 | 50.5 GB | 54–82 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4080 (16GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →
Ran Gemma 4 26B-A4B (MoE) on a NVIDIA RTX 4080 (16GB)? Add your real numbers →