Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Qwen3 14B?
Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 14B at Q6_K · 12.1 GB · 13–20 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 5.8 GB | 25–37 tok/s | Runs great |
| Q3_K_M | 7.3 GB | 20–30 tok/s | Runs great |
| Q4_K_M | 9.0 GB | 17–26 tok/s | Runs great |
| Q5_K_M | 10.5 GB | 15–23 tok/s | Runs great |
| Q6_K | 12.1 GB | 13–20 tok/s | Runs great |
| Q8_0 | 15.7 GB | 11–16 tok/s | Tight / slow |
| FP16 | 29.5 GB | 6–9 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsQwen3 14B on other machinesWhat to buy to run it →
Ran Qwen3 14B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →