Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Llama 3.1 8B?
Llama · Llama 3.1 Community · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 64–97 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 2.6 GB | 140–209 tok/s | Runs great |
| Q3_K_M | 3.5 GB | 120–179 tok/s | Runs great |
| Q4_K_M | 4.9 GB | 97–145 tok/s | Runs great |
| Q5_K_M | 5.7 GB | 87–130 tok/s | Runs great |
| Q6_K | 6.6 GB | 78–117 tok/s | Runs great |
| Q8_0 | 8.5 GB | 64–97 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsLlama 3.1 8B on other machinesWhat to buy to run it →
Ran Llama 3.1 8B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →