Qwen/Qwen3-VL-30B-A3B-Instruct

Qwen3-VL-30B-A3B-Instruct is a 30 billion parameter vision-language model developed by Qwen, featuring comprehensive upgrades for multimodal understanding and generation. This model excels in visual perception, reasoning, and agent interaction, supporting an extended context length of 32768 tokens. It is designed for tasks requiring deep visual and textual comprehension, including visual coding, spatial perception, and long-context video analysis.