CohereForAI / aya-expanse family / text-generation
aya-expanse-8b
CohereForAI/aya-expanse-8b
Benchmarks
Where it scores.
General Provisional
65.4
Coding Provisional
65.4
Math Provisional
65.4
Reasoning Provisional
65.4
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| FP16 / smallest | SAFETENSORS | 1.2 GB | — | model-00004-of-00004.safetensors |
| FP16 | SAFETENSORS | 4.9 GB | — | model-00001-of-00004.safetensors |
| FP16 | SAFETENSORS | 4.9 GB | — | model-00002-of-00004.safetensors |
| FP16 | SAFETENSORS | 5.0 GB | — | model-00003-of-00004.safetensors |
Sizes are file sizes, not peak runtime memory.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| Arena | ArenaScore | 1223.1 | 65.4 |
From the Hugging Face model card
About this model.
From the Hugging Face model card