Can I run this LLM?
Can a NVIDIA RTX 3080 (10GB) run Gemma 4 E4B?
Gemma · Apache 2.0 · estimated for a 10.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 E4B at Q6_K · 7.1 GB · 95–142 tok/s on a NVIDIA RTX 3080 (10GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 4.1 GB | 137–205 tok/s | Runs great |
| Q4_K_M | 5.0 GB | 120–181 tok/s | Runs great |
| Q5_K_M | 5.5 GB | 113–170 tok/s | Runs great |
| Q6_K | 7.1 GB | 95–142 tok/s | Runs great |
| Q8_0 | 8.2 GB | 85–128 tok/s | Won't fit |
| FP16 | 15.1 GB | 53–79 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 3080 (10GB) runsGemma 4 E4B on other machinesWhat to buy to run it →
Ran Gemma 4 E4B on a NVIDIA RTX 3080 (10GB)? Add your real numbers →