---
license: apache-2.0
base_model:
- Qwen/Qwen3-4B-Thinking-2507
pipeline_tag: text-generation
tags:
- cot
- code
- gpt_oss
- conversational
- distillation
- math
---
This is the bf16 safetensors variant
![Distil gpt oss logo](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/RxoOFH7vZmoyyKOUlB_oX.png)

# What it is
DistilGPT-OSS-qwen3-4B is a Qwen3 4B-2507 thinking fine tune, it supports up to **256K** tokens of input and output (aka total context) and can think for up to **65536** tokens when set to **high** reasoning effort. unlike the original qwen3, this model was fine-tuned on GPT-OSS reasoning outputs (unlike Deepseek r1 outputs which qwen3 was probably fine-tuned on for advanced reasoning). By fine-tuning on GPT-OSS outputs, the model was able to learn how to think efficiently, follow instructions better, and the new ability to think with a certain effort based on how much you want it to think.

⚠️This model is NOT as censored as the original GPT-OSS, we focused on performance rather than censorship. The model is still safety trained, it would just allow for more *"creative"* prompts, unlike GPT-OSS. We are not responsible for what the model generates.

Keep in mind, this is a community project and we are NOT related to qwen by Alibaba nor GPT-OSS by OpenAi.

# Format
This is the chat format of this model (you can also check the Jinja template file in "Files and versions"):
```
<|im_start|>system
You are a helpful assistant


Reasoning effort: low<|im_end|>
<|im_start|>user
Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,<|im_end|>
<|im_start|>assistant
<think>
Just continue: 13,21,34,...
</think>
The Fibonacci sequence continues by adding the two preceding numbers.  
After **8** the next term is **13** (1 + 8 = 9 – 1 = 8 + 5 = 13), then **21** (8 + 13 = 21), followed by **34** (13 + 21 = 34), and so on.

So the sequence starts:  

**1, 1, 2, 3, 5, 8, 13, 21, 34, …**<|im_end|>
```

As you can see, you set the reasoning effort via the system prompt. We recommend going **2** lines down and only then putting "Reasoning effort: [low,medium,high]. For your information that output was generated by our model.

# Examples

1) "Is a banana an animal?" Reasoning was set to **high**.
![Is a banana an animal?](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/f1N8knMusup4dugZ2WREB.png)
2) "Make an HTML website about yourself" Reasoning was set to **medium**.
![Write an HTML website about yourself](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/azInLvZ1KGpT5DXT2zCyV.png)
3) "translate this to chinese: Hello! I am ChatGPT. A large language model by OpenAi." Reasoning was set to **low**.
![translate this to chinese: Hello! I am ChatGPT. A large language model by OpenAi.](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/YH4Q0UY3aqeHRNhOgWv_V.png)

As you can see, based on the reasoning effort of the model and your prompt, the model would think for a different amount of time.
Keep in mind, these tests were done in LM Studio, GGUF q8_0 on a single consumer card (rtx 3080) where we got 95 - 80 Tokens/Second on 8192 context.

# Additional information

The model was trained using unsloth, using a mix of private datasets and public datasets.