Can I run this LLM?
Can a NVIDIA RTX 4090 (24GB) run Gemma 2 2B?
Gemma · Gemma · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 2 2B at Q8_0 · 2.8 GB · 142–213 tok/s on a NVIDIA RTX 4090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q4_K_M | 1.6 GB | 184–276 tok/s | Runs great |
| Q5_K_M | 1.9 GB | 172–258 tok/s | Runs great |
| Q6_K | 2.2 GB | 161–242 tok/s | Runs great |
| Q8_0 | 2.8 GB | 142–213 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsGemma 2 2B on other machinesWhat to buy to run it →
Ran Gemma 2 2B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →