Can I run this LLM?
Can a NVIDIA RTX 3090 (24GB) run Llama 3.1 8B?
Llama · Llama 3.1 Community · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 63–95 tok/s on a NVIDIA RTX 3090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 2.6 GB | 137–206 tok/s | Runs great |
| Q3_K_M | 3.5 GB | 117–176 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 95–142 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 85–127 tok/s | Runs great |
| Q6_K | 6.6 GB | 76–115 tok/s | Runs great |
| Q8_0 | 8.5 GB | 63–95 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) runsLlama 3.1 8B on other machinesWhat to buy to run it →
Ran Llama 3.1 8B on a NVIDIA RTX 3090 (24GB)? Add your real numbers →