ai/qwen3-vl

Qwen3 VL

GGUF version by Unsloth

!https://github.com/docker/model-cards/raw/refs/heads/main/logos/***

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.

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:

!https://github.com/docker/model-cards/raw/refs/heads/main/images/qwen3vl_arc.jpg

1. Interleaved-MRoPE: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning.
2. DeepStack: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment.
3. Text–Timestamp Alignment: Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling.

This is the weight repository for Qwen3-VL-8B-Instruct.

Available model variants

¹: VRAM estimated based on model characteristics.

latest → 8B

🐳 Using this model with Docker Model Runner

Run the model:

bash
docker model run ai/qwen3-vl

For more information, check out the Docker Model Runner docs.

🔗 Links

• https://github.com/QwenLM/Qwen3-VL
• Unsloth Dynamic 2.0 GGUF
• How to fine-tune