Changelog

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen3-VL/llms.txt

Use this file to discover all available pages before exploring further.

​

2025

​

November 27, 2025 - Technical Paper Release

• Interleaved-MRoPE architecture
• DeepStack multi-level feature fusion
• Text-Timestamp alignment for videos
• Training data and methodology
• Comprehensive benchmark evaluations
• Ablation studies

• Paper: arXiv:2511.21631
• Blog: Qwen AI Blog

​

October 21, 2025 - Qwen3-VL 2B & 32B Models

• Qwen3-VL-2B-Instruct (HuggingFace)
• Qwen3-VL-2B-Thinking (HuggingFace)
• Qwen3-VL-32B-Instruct (HuggingFace)
• Qwen3-VL-32B-Thinking (HuggingFace)

• 2B models suitable for edge deployment and consumer GPUs
• 32B models provide high performance with reasonable resource requirements
• Both Instruct and Thinking editions available
• Available on both HuggingFace and ModelScope

​

October 15, 2025 - Qwen3-VL 4B & 8B Models

• Qwen3-VL-4B-Instruct (HuggingFace)
• Qwen3-VL-4B-Thinking (HuggingFace)
• Qwen3-VL-8B-Instruct (HuggingFace)
• Qwen3-VL-8B-Thinking (HuggingFace)

• Balanced performance-to-resource ratio
• 4B suitable for RTX 3090/4090 GPUs
• 8B provides strong capabilities for professional use
• Both editions support full feature set

​

October 4, 2025 - MoE Models & FP8 Quantization

• Qwen3-VL-30B-A3B-Instruct (HuggingFace)
• Qwen3-VL-30B-A3B-Thinking (HuggingFace)

• 30B total parameters, 3B active per token
• Efficient inference with MoE architecture
• FP8 models available in collections:
  • HuggingFace Collection
  • ModelScope Collection

​

September 23, 2025 - Qwen3-VL 235B Launch

• Qwen3-VL-235B-A22B-Instruct (HuggingFace)
• Qwen3-VL-235B-A22B-Thinking (HuggingFace)

• State-of-the-art vision-language performance
• 235B parameters, 22B active (MoE)
• Native 256K context, expandable to 1M
• Advanced capabilities:
  • Visual agent (PC/mobile GUI interaction)
  • Visual coding (Draw.io, HTML/CSS/JS)
  • 3D grounding and spatial reasoning
  • Enhanced video understanding
  • 32-language OCR
  • Superior multimodal reasoning

​

April 8, 2025 - Fine-tuning Code Release

• Code: qwen-vl-finetune
• Supports custom visual tasks
• LoRA and full fine-tuning

​

March 25, 2025 - Qwen2.5-VL-32B

• Smarter responses
• Better human preference alignment
• Enhanced reasoning capabilities

​

February 20, 2025 - Qwen2.5-VL Technical Report

• Qwen2.5-VL-3B-Instruct-AWQ
• Qwen2.5-VL-7B-Instruct-AWQ
• Qwen2.5-VL-72B-Instruct-AWQ

​

January 28, 2025 - Qwen2.5-VL Series

• Qwen2.5-VL-3B-Instruct
• Qwen2.5-VL-7B-Instruct
• Qwen2.5-VL-72B-Instruct

​

2024

​

December 25, 2024 - QvQ-72B-Preview

• 72B parameters
• Advanced visual reasoning capabilities
• Research preview for community feedback

​

September 19, 2024 - Qwen2-VL-72B

• Qwen2-VL-72B-Instruct
• Qwen2-VL-72B-Instruct-AWQ
• Qwen2-VL-72B-Instruct-GPTQ-Int4
• Qwen2-VL-72B-Instruct-GPTQ-Int8

​

August 30, 2024 - Qwen2-VL Series Launch

• Qwen2-VL-2B-Instruct
• Qwen2-VL-7B-Instruct
• (72B announced, released later)

• Multi-resolution image understanding
• Video support
• Enhanced OCR
• Improved multimodal reasoning

​

Release Timeline Summary

​

Migration Guides

​

From Qwen2.5-VL to Qwen3-VL

1. Patch size: 14 → 16
   # Update qwen-vl-utils calls
   process_vision_info(messages, image_patch_size=16)  # was 14
   
2. Video metadata: New return format
   images, videos, video_kwargs = process_vision_info(
       messages,
       image_patch_size=16,
       return_video_kwargs=True,
       return_video_metadata=True  # New for Qwen3-VL
   )
   
3. Architecture improvements: Interleaved-MRoPE, DeepStack, Text-Timestamp alignment
4. New capabilities:
   • 3D grounding
   • Enhanced visual coding
   • Better spatial reasoning
   • Extended OCR (32 languages)

​

From Qwen2-VL to Qwen3-VL

• Significantly improved performance across all tasks
• Native long context (256K vs 32K)
• Video understanding enhancements
• New architectures (MoE, Thinking editions)
• Broader model size range (2B-235B)

​

Future Roadmap

• Additional model sizes and variants
• Enhanced fine-tuning tools and examples
• More cookbook examples and tutorials
• Extended language support for OCR
• Performance optimizations
• Community-contributed extensions

​

Resources

​

Documentation

• Installation Guide
• Quickstart
• Model Cards
• Benchmarks

​

Code & Models

• GitHub Repository
• HuggingFace Collection
• ModelScope Collection
• Cookbooks

​

Papers

• Qwen3-VL Technical Report (2025)
• Qwen2.5-VL Technical Report (2025)
• Qwen2-VL Paper (2024)

​

Community

• Discord
• WeChat Group
• GitHub Discussions

​

Citation

@article{Qwen3-VL,
  title={Qwen3-VL Technical Report},
  author={Qwen Team},
  journal={arXiv preprint arXiv:2511.21631},
  year={2025}
}