Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 27B at Q8_0 · 28.6 GB · 22–34 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 11.6 GB | 49–73 tok/s | Runs great |
| Q4_K_M | 16.3 GB | 37–55 tok/s | Runs great |
| Q5_K_M | 19.2 GB | 32–48 tok/s | Runs great |
| Q6_K | 22.2 GB | 28–42 tok/s | Runs great |
| Q8_0 | 28.6 GB | 22–34 tok/s | Runs great |
| FP16 | 53.8 GB | 12–19 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →