# Hugging Face — A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

- Company: Hugging Face (huggingface.co)
- Announced: 2025-03-04T00:00:00+00:00
- Category: new-model
- Subject: Platform
- Open weights: yes
- Models affected: Aya Vision 8B, Aya Vision 32B
- Source: https://huggingface.co/blog/aya-vision
- Record: https://forck.live/items/1737-a-deepdive-into-aya-vision-advancing-the-frontier-of-multilingual-multimodality

Cohere For AI announces Aya Vision, a new open-weight multilingual multimodal model family with 8B and 32B parameter variants, designed for vision-language understanding across 23 languages. The models outperform larger models in pairwise comparisons and are released as open weights for research.

## Evidence

Verbatim from https://huggingface.co/blog/aya-vision:

> With the release of the Aya Vision family, our new 8B and 32B parameter vision-language models (VLMs), we are addressing one of the biggest challenges in AI: bringing multilingual performance to multimodal models.

---

Record: https://forck.live/items/1737-a-deepdive-into-aya-vision-advancing-the-frontier-of-multilingual-multimodality
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md