Ornith Models — Hardware Requirements
3 Ornith models from Deep Reinforce and the community, from the smallest that runs in 3.7 GB of VRAM up to 396.8B parameters. Every row links to full quantization tables and GPU compatibility.
All Ornith Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Ornith 1.0 9B | 9.4B | 3.7 GB | 262K | ||
| Ornith 1.0 35B | 35.1B | 10.0 GB | 262K | ||
| Ornith 1.0 35B AEON Ultimate Uncensored BF16 | 35.1B | 15.3 GB | 262K | ||
| Ornith 1.0 397B | 396.8B | 109.5 GB | 262K |
Frequently Asked Questions
- How much VRAM do I need to run a Ornith model?
- The smallest Ornith model, Ornith 1.0 9B, runs from 3.7 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Ornith models can I run on a 16 GB GPU?
- 3 of 4 Ornith models fit in 16 GB of VRAM at some quantization, including Ornith 1.0 35B, Ornith 1.0 9B, Ornith 1.0 35B AEON Ultimate Uncensored BF16.
- What is the most popular Ornith model to run locally?
- Ornith 1.0 35B is the most downloaded Ornith model in local-friendly quantized formats. It runs from 10.0 GB of VRAM.