← All Models

Qwen3-VL

20.7K Downloads

Qwen's latest vision-language model. Includes comprehensive upgrades to visual perception, spatial reasoning, and image understanding.

Models
Updated Just now
qwen/qwen3-vl-2b
3.00 GB
qwen/qwen3-vl-4b
3.00 GB
qwen/qwen3-vl-8b
6.00 GB
qwen/qwen3-vl-30b
18.40 GB
qwen/qwen3-vl-32b
20.00 GB

Memory Requirements

To run the smallest Qwen3-VL, you need at least 3 GB of RAM. The largest one may require up to 20 GB.

Capabilities

Qwen3-VL models support tool use and vision input. They are available in mlx.

About Qwen3-VL

undefined

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment.

Key Enhancements:

  • Visual Agent: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks.

  • Visual Coding Boost: Generates Draw.io/HTML/CSS/JS from images/videos.

  • Advanced Spatial Perception: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.

  • Long Context & Video Understanding: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.

  • Enhanced Multimodal Reasoning: Excels in STEM/Math—causal analysis and logical, evidence-based answers.

  • Upgraded Visual Recognition: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc.

  • Expanded OCR: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.

  • Text Understanding on par with pure LLMs: Seamless text–vision fusion for lossless, unified comprehension.

Model Architecture Updates:

undefined

  • Interleaved-MRoPE: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.

  • DeepStack: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.

  • Text–Timestamp Alignment: Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.

Multimodal Performance

undefined

Qwen3-VL delivers strong vision-language performance across diverse tasks including document analysis, visual question answering, video understanding, and agentic interactions. Suitable for edge deployment with efficient inference on Apple Silicon via MLX quantization.