inclusionAI releases LingSante-3.1-air-VL vision-language model on Hugging Face

rohanpaul_ai · x · 2026-11-23

Ant Group's inclusionAI team has published LingSante-3.1-air-VL, a vision-language model, on Hugging Face. The model's chat template shows native support for multimodal content, toggleable thinking modes (enablethinking / preservethinking), tool calling, and image/video counters.

Original post →

More from Multimodal

Multimodal channel →