Qwen3-VL-30B

Qwen3 VL 30B

The latest generation vision-language MoE model in the Qwen series with comprehensive upgrades to visual perception, spatial reasoning, and video understanding.

Key Features

• Visual Agent: Operates PC and mobile GUIs—recognizes elements, understands functions, and completes tasks
• Visual Coding: Generates Draw.io, HTML, CSS, and JavaScript from images and videos
• Advanced Spatial Perception: Provides 2D/3D grounding for spatial reasoning and embodied AI applications
• Upgraded Recognition: Recognizes celebrities, anime, products, landmarks, flora, fauna, and more
• Expanded OCR: Supports 32 languages with robust performance in low light, blur, and tilt conditions
• Pure Text Performance: Text understanding on par with pure LLMs through seamless text-vision fusion
• High-Efficiency MoE: 31.1B total parameters with only 3B activated (A3B) for excellent efficiency

Architecture Highlights

• 31.1B total parameters (3B activated per token)
• Mixture-of-Experts architecture
• Interleaved-MRoPE for enhanced video reasoning
• DeepStack for fine-grained detail capture
• Text-Timestamp Alignment for precise event localization
• Context length: 256,000 tokens
• Vision-enabled multimodal MoE model

Performance

Delivers superior vision-language performance across diverse tasks including document analysis, visual question answering, video understanding, and agentic interactions. The MoE architecture provides excellent efficiency while maintaining high-quality outputs.