---
base_model: unsloth/Qwen3-4B-Thinking-2507
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
datasets:
- TeichAI/gpt-5.2-high-reasoning-250x
---

# Qwen3 4B Thinking 2507 x GPT 5.2 (High Reasoning)

This model was trained on 250 examples generated by GPT 5.2 (high reasoning)

Note: In this distill I fixed formatting issues found in previous gpt 5 distills. Will be going back to update the other 5.2 distills

- **Developed by:** TeichAI
- **Finetuned from model :** unsloth/qwen3-4b-thinking-2507

This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.