Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run Ornith 1.5 35B-A3B (MoE)?
Ornith · MIT · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.5 35B-A3B (MoE) at FP16 · 71.1 GB · 26–39 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 13.1 GB | 81–122 tok/s | Runs great |
| Q3_K_M | 16.7 GB | 72–107 tok/s | Runs great |
| Q4_K_M | 21.9 GB | 61–92 tok/s | Runs great |
| Q5_K_M | 25.5 GB | 56–83 tok/s | Runs great |
| Q6_K | 30.5 GB | 49–74 tok/s | Runs great |
| Q8_0 | 37.8 GB | 42–63 tok/s | Runs great |
| FP16 | 71.1 GB | 26–39 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsOrnith 1.5 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →