Aya 23 8B
Cohere's multilingual research model covering 23 languages. CC-BY-NC — research only.
Overview
Cohere's multilingual research model covering 23 languages. CC-BY-NC — research only.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- 23 languages
- Research-friendly
Weaknesses
- Non-commercial license
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 5.0 GB | 8 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Aya 23 8B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Aya 23 8B?
Can I use Aya 23 8B commercially?
What's the context length of Aya 23 8B?
Source: huggingface.co/CohereLabs/aya-23-8B
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Aya 23 8B runs on your specific hardware before committing money.