Aya Models — Hardware Requirements
4 Aya models from Cohere and the community, from the smallest that runs in 7.4 GB of VRAM up to 8.0B parameters. Every row links to full quantization tables and GPU compatibility.
All Aya Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Tiny Aya Global | 3.3B | 7.4 GB | — | ||
| Tiny Aya Water | 3.3B | 7.4 GB | — | ||
| Aya Expanse 8B | 8.0B | 17.7 GB | — | ||
| Aya 23 8B | 8.0B | 17.7 GB | — |
Frequently Asked Questions
- How much VRAM do I need to run a Aya model?
- The smallest Aya model, Tiny Aya Global, runs from 7.4 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Aya models can I run on a 16 GB GPU?
- 2 of 4 Aya models fit in 16 GB of VRAM at some quantization, including Tiny Aya Global, Tiny Aya Water.
- What is the most popular Aya model to run locally?
- Aya Expanse 8B is the most downloaded Aya model in local-friendly quantized formats. It runs from 17.7 GB of VRAM.