Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Gemma 4 26B-A4B (MoE)?
Gemma · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 26B-A4B (MoE) at Q8_0 · 26.8 GB · 89–134 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 10.9 GB | 131–196 tok/s | Runs great |
| Q4_K_M | 15.3 GB | 116–174 tok/s | Runs great |
| Q5_K_M | 18.0 GB | 108–163 tok/s | Runs great |
| Q6_K | 20.8 GB | 101–152 tok/s | Runs great |
| Q8_0 | 26.8 GB | 89–134 tok/s | Runs great |
| FP16 | 50.5 GB | 61–91 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →
Ran Gemma 4 26B-A4B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →