Can I run this LLM?
Can a NVIDIA RTX 3090 (24GB) run Ornith 1.5 35B-A3B (MoE)?
Ornith · MIT · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ornith 1.5 35B-A3B (MoE) at Q3_K_M · 16.7 GB · 204–306 tok/s on a NVIDIA RTX 3090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 13.1 GB | 224–336 tok/s | Runs great |
| Q3_K_M | 16.7 GB | 204–306 tok/s | Runs great |
| Q4_K_M | 21.9 GB | 181–271 tok/s | Won't fit |
| Q5_K_M | 25.5 GB | 167–251 tok/s | Won't fit |
| Q6_K | 30.5 GB | 152–228 tok/s | Won't fit |
| Q8_0 | 37.8 GB | 134–201 tok/s | Won't fit |
| FP16 | 71.1 GB | 87–130 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) runsOrnith 1.5 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA RTX 3090 (24GB)? Add your real numbers →