Can I run this LLM?
Can a NVIDIA H200 (141GB) run Ornith 1.0 35B (MoE)?
Ornith · MIT · estimated for a 141.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.0 35B (MoE) at FP16 · 69.4 GB · 222–332 tok/s on a NVIDIA H200 (141GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 16.7 GB | 310–465 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 298–446 tok/s | Runs great |
| Q5_K_M | 26.5 GB | 289–433 tok/s | Runs great |
| Q6_K | 29.3 GB | 283–424 tok/s | Runs great |
| Q8_0 | 36.9 GB | 269–403 tok/s | Runs great |
| FP16 | 69.4 GB | 222–332 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA H200 (141GB) runsOrnith 1.0 35B (MoE) on other machinesWhat to buy to run it →
Ran Ornith 1.0 35B (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →