Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Qwen3 32B?
Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 32B at Q2_K · 12.3 GB · 13–19 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.3 GB | 13–19 tok/s | Runs great |
| Q3_K_M | 16.0 GB | 10–15 tok/s | Tight / slow |
| Q4_K_M | 19.8 GB | 8–13 tok/s | Tight / slow |
| Q5_K_M | 23.2 GB | 7–11 tok/s | Tight / slow |
| Q6_K | 26.9 GB | 6–10 tok/s | Tight / slow |
| Q8_0 | 34.8 GB | 5–7 tok/s | Tight / slow |
| FP16 | 65.5 GB | 3–4 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsQwen3 32B on other machinesWhat to buy to run it →
Ran Qwen3 32B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →