# Multilingual Image Understanding

Llama 4 Scout is a 17-billion-parameter multimodal model with a Mixture of Experts (MoE) architecture, introduced by Meta. It supports 12 languages and image understanding, featuring a topk=4 expert dynamic fusion mechanism.

Llama 4 Scout is a multimodal mixture-of-experts model developed by Meta, supporting 12 languages and image understanding, with 17 billion active parameters and a 10M context length.

Chitrarth is a multilingual vision-language model designed to connect vision and language, with a special focus on supporting multiple Indian languages.

PaliGemma is a lightweight and versatile vision-language model built on the SigLIP vision model and Gemma language model, supporting multilingual image-text interaction tasks.

PaliGemma is a versatile lightweight vision-language model (VLM) built upon SigLIP vision model and Gemma language model, capable of processing both image and text inputs to generate text outputs.