> This page is for version v2 API (default).
> For other versions, use one of these documentation indexes:
> - v2 API (default): https://docs.cohere.com/v2/llms.txt
> - v1 API: https://docs.cohere.com/v1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# Tiny Aya

> Tiny Aya is a compact yet powerful 3.35B-parameter multilingual model supporting 70 languages, designed for efficient and practical multilingual AI deployment.

Tiny Aya is a compact 3.35-billion parameter multilingual model that achieves state-of-the-art translation quality, strong multilingual understanding, and high-quality target-language generation across 70 languages. Despite its small size, Tiny Aya is designed to run locally on any device — including phones — without requiring cloud dependency.

Tiny Aya represents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment rather than simply increasing parameters.

## Supported Languages

Tiny Aya supports 70 languages: English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Nepali, Tagalog, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba, and Zulu.

## Model Variants

Tiny Aya is released as a family of five models: a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized variants.

| Model Name        | Description                                         | Languages | Parameters | Context Length | Maximum Output Tokens |
| ----------------- | --------------------------------------------------- | --------- | ---------- | -------------- | --------------------- |
| `tiny-aya-base`   | Pretrained foundation model for multilingual tasks. | 70        | 3.35B      | 8k             | 8k                    |
| `tiny-aya-global` | Best balance across languages and regions.          | 70        | 3.35B      | 8k             | 8k                    |
| `tiny-aya-earth`  | Best for West Asian and African languages.          | 70        | 3.35B      | 8k             | 8k                    |
| `tiny-aya-fire`   | Best for South Asian languages.                     | 70        | 3.35B      | 8k             | 8k                    |
| `tiny-aya-water`  | Best for European and Asia-Pacific languages.       | 70        | 3.35B      | 8k             | 8k                    |

## Key Capabilities

Tiny Aya excels at the following tasks:

* **Translation**: State-of-the-art multilingual translation quality across 70 languages.
* **Multilingual understanding**: Strong performance on multilingual comprehension benchmarks.
* **Target-language generation**: High-quality text generation in the target language.
* **On-device deployment**: Compact enough to run locally on phones and edge devices.

## How Can I Access Tiny Aya?

The instruction-tuned Tiny Aya variants (`tiny-aya-global`, `tiny-aya-earth`, `tiny-aya-fire`, `tiny-aya-water`) are available on the Cohere API via the [Chat endpoint](/reference/chat). You can use them with the Cohere SDK just like any other model:

**`PYTHON`**

```python PYTHON
import cohere

co = cohere.ClientV2("<YOUR_API_KEY>")

response = co.chat(
    model="tiny-aya-global",
    messages=[
        {
            "role": "user",
            "content": "Bonjour! Pouvez-vous me raconter une courte histoire en français?",
        }
    ],
)

print(response.message.content[0].text)
```

Tiny Aya is also available as open-weight models through Hugging Face. You can download and run the models locally:

* [tiny-aya-base](https://huggingface.co/CohereLabs/tiny-aya-base)
* [tiny-aya-global](https://huggingface.co/CohereLabs/tiny-aya-global)
* [tiny-aya-earth](https://huggingface.co/CohereLabs/tiny-aya-earth)
* [tiny-aya-fire](https://huggingface.co/CohereLabs/tiny-aya-fire)
* [tiny-aya-water](https://huggingface.co/CohereLabs/tiny-aya-water)

GGUF quantized versions are also available for efficient local inference:

* [tiny-aya-global-GGUF](https://huggingface.co/CohereLabs/tiny-aya-global-GGUF)
* [tiny-aya-earth-GGUF](https://huggingface.co/CohereLabs/tiny-aya-earth-GGUF)
* [tiny-aya-fire-GGUF](https://huggingface.co/CohereLabs/tiny-aya-fire-GGUF)
* [tiny-aya-water-GGUF](https://huggingface.co/CohereLabs/tiny-aya-water-GGUF)

## Find More

* [Tiny Aya research paper](https://cohere.com/research/papers/tiny-aya-bridging-scale-and-multilingual-depth-2026-02-17)
* [Blog post: Cohere Labs Launches Tiny Aya](https://cohere.com/blog/cohere-labs-tiny-aya)
* [Aya research initiative](https://cohere.com/research/aya)