1. Tutorial Introduction

Qwen3-4B-Thinking-2507 and Qwen3-4B-Instruct-2507 are large language models launched by Alibaba's Tongyi Qianwen team in August 2025. In terms of performance, Qwen3-4B-Thinking-2507 significantly outperforms smaller Qwen3 models of similar size in complex problem reasoning, mathematical ability, coding ability, and multi-turn function call capabilities. In the non-reasoning domain, Qwen3-4B-Instruct-2507 comprehensively surpasses the closed-source small-sized model GPT-4.1-nano in knowledge, reasoning, programming, alignment, and agency capabilities, and its performance is close to that of the medium-sized Qwen3-30B-A3B (non-thinking). This model covers more long-tail language knowledge, enhances alignment with human preferences in subjective and open-ended tasks, and can provide more relevant responses. Related paper results are... Qwen3 Technical Report .

This tutorial uses dual-card RTX 4090 resources.

2. Project Examples

Qwen3-4B-Thinking-2507 

Qwen3-4B-Instruct-2507 

3. Operation steps

1. After starting the container, click the API address to enter the Web interface

2. After entering the webpage, you can start a conversation with the model

If "Model" is not displayed, it means the model is being initialized. Since the model is large, please wait about 2-3 minutes and refresh the page.

How to use

Qwen3-4B-Thinking-2507

Qwen3-4B-Instruct-2507

4. Discussion

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [SD Tutorial] to join the group to discuss various technical issues and share application effects↓

Citation Information

The citation information for this project is as follows:

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}