Can I run this LLM?
Can a NVIDIA RTX 5060 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 · 24–36 tok/s on a NVIDIA RTX 5060 Ti (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.8 GB | 24–36 tok/s | Tight / slow |
| Q3_K_M | 14.7 GB | 20–30 tok/s | Won't fit |
| Q4_K_M | 18.3 GB | 16–24 tok/s | Won't fit |
| Q5_K_M | 21.7 GB | 14–21 tok/s | Won't fit |
| Q6_K | 25.2 GB | 12–18 tok/s | Won't fit |
| Q8_0 | 32.6 GB | 10–14 tok/s | Won't fit |
| FP16 | 61.4 GB | 5–8 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5060 Ti (16GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a NVIDIA RTX 5060 Ti (16GB)? Add your real numbers →