Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?
Nemotron · openmdw-1.1 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at FP16 · 65.9 GB · 26–39 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 65–98 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 63–95 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 54–81 tok/s | Runs great |
| Q5_K_M | 27.0 GB | 52–78 tok/s | Runs great |
| Q6_K | 34.3 GB | 44–65 tok/s | Runs great |
| Q8_0 | 35.0 GB | 43–64 tok/s | Runs great |
| FP16 | 65.9 GB | 26–39 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsNemotron 3.5 Lightning 30B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →