Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Gemma 3 12B?
Gemma · Gemma · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 3 12B at FP16 · 23.5 GB · 26–39 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.8 GB | 85–128 tok/s | Runs great |
| Q3_K_M | 6.0 GB | 74–111 tok/s | Runs great |
| Q4_K_M | 7.3 GB | 65–98 tok/s | Runs great |
| Q5_K_M | 8.5 GB | 59–89 tok/s | Runs great |
| Q6_K | 9.7 GB | 54–81 tok/s | Runs great |
| Q8_0 | 12.5 GB | 44–66 tok/s | Runs great |
| FP16 | 23.5 GB | 26–39 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsGemma 3 12B on other machinesWhat to buy to run it →
Ran Gemma 3 12B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →