Can I run this LLM?
Can a NVIDIA RTX 5070 Ti (16GB) run Gemma 4 31B?
Gemma · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Gemma 4 31B at Q2_K · 11.8 GB · 45–67 tok/s on a NVIDIA RTX 5070 Ti (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.8 GB | 45–67 tok/s | Tight / slow |
| Q3_K_M | 14.7 GB | 37–56 tok/s | Won't fit |
| Q4_K_M | 18.3 GB | 31–47 tok/s | Won't fit |
| Q5_K_M | 21.7 GB | 27–40 tok/s | Won't fit |
| Q6_K | 25.2 GB | 23–35 tok/s | Won't fit |
| Q8_0 | 32.6 GB | 19–28 tok/s | Won't fit |
| FP16 | 61.4 GB | 10–15 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5070 Ti (16GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a NVIDIA RTX 5070 Ti (16GB)? Add your real numbers →