Can I run this LLM?
Can a NVIDIA RTX 4080 (16GB) run Ornith 1.5 35B-A3B (MoE)?
Ornith · MIT · estimated for a 16.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Ornith 1.5 35B-A3B (MoE) at Q2_K · 13.1 GB · 201–301 tok/s on a NVIDIA RTX 4080 (16GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 13.1 GB | 201–301 tok/s | Tight / slow |
| Q3_K_M | 16.7 GB | 180–270 tok/s | Won't fit |
| Q4_K_M | 21.9 GB | 157–235 tok/s | Won't fit |
| Q5_K_M | 25.5 GB | 144–215 tok/s | Won't fit |
| Q6_K | 30.5 GB | 129–193 tok/s | Won't fit |
| Q8_0 | 37.8 GB | 112–168 tok/s | Won't fit |
| FP16 | 71.1 GB | 70–105 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4080 (16GB) 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 4080 (16GB)? Add your real numbers →