LLM
Qwen 3.8 Max VL
Qwen 3.8 Max VLAlibaba’s vision-language model for image understanding and text generation, with optional reasoning and OpenAI-compatible inference on dedicated GPUs.
Model details
Qwen 3.8 Max VL is Alibaba’s vision-language mixture-of-experts model for working with images and text. Use it to describe visual content, answer questions about images, and build multimodal applications with optional reasoning.
