Can I run this LLM?
Can a NVIDIA RTX 3080 (10GB) run Gemma 3 12B?
Gemma · Gemma · estimated for a 10.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 3 12B at Q2_K · 4.8 GB · 71–106 tok/s on a NVIDIA RTX 3080 (10GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.8 GB | 71–106 tok/s | Runs great |
| Q3_K_M | 6.0 GB | 61–92 tok/s | Tight / slow |
| Q4_K_M | 7.3 GB | 54–81 tok/s | Won't fit |
| Q5_K_M | 8.5 GB | 48–73 tok/s | Won't fit |
| Q6_K | 9.7 GB | 44–66 tok/s | Won't fit |
| Q8_0 | 12.5 GB | 36–54 tok/s | Won't fit |
| FP16 | 23.5 GB | 21–32 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 3080 (10GB) runsGemma 3 12B on other machinesWhat to buy to run it →
Ran Gemma 3 12B on a NVIDIA RTX 3080 (10GB)? Add your real numbers →