Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Ornith 1.0 35B (MoE)?
Ornith · MIT · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.0 35B (MoE) at FP16 · 69.4 GB · 25–37 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 16.7 GB | 65–97 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 55–83 tok/s | Runs great |
| Q5_K_M | 26.5 GB | 50–75 tok/s | Runs great |
| Q6_K | 29.3 GB | 47–70 tok/s | Runs great |
| Q8_0 | 36.9 GB | 40–60 tok/s | Runs great |
| FP16 | 69.4 GB | 25–37 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsOrnith 1.0 35B (MoE) on other machinesWhat to buy to run it →
Ran Ornith 1.0 35B (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →