Orca Models — Hardware Requirements
9 Orca models from pankajmathur and the community, from the smallest that runs in 2.3 GB of VRAM at Q4 up to 3.4B parameters. Every row links to full quantization tables and GPU compatibility.
All Orca Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Orca Mini 3B | 3.4B | 2.3 GB | 2K | ||
| OrcaSAQ 2 27B | 6.8B | 6.9 GB | 262K |
Frequently Asked Questions
- How much VRAM do I need to run a Orca model?
- The smallest Orca model, Orca Mini 3B, runs from 2.3 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 1.6 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which Orca models can I run on a 16 GB GPU?
- 2 of 2 Orca models fit in 16 GB of VRAM at Q4_K_M, including OrcaSAQ 2 27B, Orca Mini 3B.
- What is the most popular Orca model to run locally?
- OrcaSAQ 2 27B is the most downloaded Orca model in local-friendly quantized formats. It runs from 6.9 GB of VRAM at Q4_K_M.