Model fiche
Aya 23 8B
By Cohere For AI · Canada
chat
general
multilingual
Overview
Cohere For AI's pre-Expanse 8B multilingual model covering 23 languages, now superseded by Aya Expanse 8B and restricted to non-commercial use.
When to pick this model
- Reproducing pre-Expanse multilingual baselines
- Research comparisons of Cohere multilingual lineage
- Non-commercial multilingual prototypes
- Teaching examples for multilingual instruction tuning
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 5 GB |
| Q5_K_M | 6 GB |
| Q8_0 | 9 GB |
| FP16 (no quantization) | 16 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
Strengths
- Solid pre-Expanse multilingual coverage
- 23 languages including French, Arabic, and Chinese
- Compact 8B footprint for the breadth
Limitations
- CC-BY-NC 4.0 license blocks commercial use
- 8k context is restrictive by current standards
- Superseded by Aya Expanse 8B in every dimension
Architecture & training
Architecture: Dense 8B · IFT on Aya Collection
Training: 23 languages.
Verdict
Skip for new work — Aya Expanse 8B replaces this model with better quality under the same license.
Quick start
ollama run aya:8bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.