SEACrowd/Gemma-SEA-LION-v4-27B-VL

Gemma-SEA-LION-v4-27B-VL is a 27 billion parameter instruct-tuned vision-text model developed by SEACrowd and AI Singapore, built on the Gemma 3 architecture. It features a large 128K context length and is specifically post-trained on approximately 540k instruction-image pairs across 11 Southeast Asian languages and English. This model excels at image and text understanding, including document comprehension, visual Q&A, and image-grounded reasoning, making it highly effective for tasks within the Southeast Asian region.