Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Qwen3.8 27B?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.8 27B at Q8_0 · 29.0 GB · 22–33 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.8 GB | 48–72 tok/s | Runs great |
| Q4_K_M | 16.6 GB | 36–54 tok/s | Runs great |
| Q5_K_M | 19.5 GB | 32–47 tok/s | Runs great |
| Q6_K | 22.5 GB | 28–42 tok/s | Runs great |
| Q8_0 | 29.0 GB | 22–33 tok/s | Runs great |
| FP16 | 54.6 GB | 12–18 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsQwen3.8 27B on other machinesWhat to buy to run it →
Ran Qwen3.8 27B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →