Can I run this LLM?
Can a NVIDIA RTX 3090 (24GB) run Ornith 1.0 35B (MoE)?
Ornith · MIT · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.0 35B (MoE) at Q3_K_M · 16.7 GB · 189–283 tok/s on a NVIDIA RTX 3090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 16.7 GB | 189–283 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 167–251 tok/s | Won't fit |
| Q5_K_M | 26.5 GB | 153–230 tok/s | Won't fit |
| Q6_K | 29.3 GB | 145–218 tok/s | Won't fit |
| Q8_0 | 36.9 GB | 128–192 tok/s | Won't fit |
| FP16 | 69.4 GB | 84–126 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) runsOrnith 1.0 35B (MoE) on other machinesWhat to buy to run it →
Ran Ornith 1.0 35B (MoE) on a NVIDIA RTX 3090 (24GB)? Add your real numbers →