Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Qwen3.6 27B?
Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Qwen3.6 27B at Q3_K_M · 13.6 GB · 12–18 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.6 GB | 12–18 tok/s | Tight / slow |
| Q4_K_M | 16.8 GB | 10–15 tok/s | Tight / slow |
| Q5_K_M | 19.5 GB | 9–13 tok/s | Tight / slow |
| Q6_K | 22.5 GB | 7–11 tok/s | Tight / slow |
| Q8_0 | 28.6 GB | 6–9 tok/s | Tight / slow |
| FP16 | 53.8 GB | 3–5 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsQwen3.6 27B on other machinesWhat to buy to run it →
Ran Qwen3.6 27B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →