---
base_model:
- Qwen/Qwen3-4B
tags:
- transformers
- qwen3
- R1
- THİNK
license: apache-2.0
language:
- en
---

[<img src="https://i.imgur.com/vo0dm9p.jpeg" width="710"/>]()


# Qwen3-R1 4B 🚀
 
-GGUF version
''
https://huggingface.co/mradermacher/Qwen3-R1-4B-GGUF

https://huggingface.co/mradermacher/Qwen3-R1-4B-i1-GGUF
''


<div align="center">
  
[![Model Size](https://img.shields.io/badge/Model%20Size-4B-red)](https://huggingface.co/Ali-Yaser/Qwen3-R1-8B)
[![License](https://img.shields.io/badge/License-Apache%20-green)](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
[![Base Model](https://img.shields.io/badge/Base-Qwen3%20-orange)](https://huggingface.co/Qwen/Qwen3-8B)

</div>

## Model Description

**Qwen3-R1 Series** is a specialized math and reansoning awnsers-focused fine-tuned version of Qwen3-8B Instruct, optimized for Math and hard question tasks. 



## 📊 Model Details

- **Developed by:** Ali-Yaser
- **Model type:** GRPO thinker 
- **Base Model:** Qwen/Qwen3-8B
- **Model Size:** 4B parameters
- **License:** Apache 2.0
- **Language(s):** English
- **Finetuned from:** Qwen3-4B

## 🚀 Quick Start

### Installation
I use a vLLM

```
# Install vLLM from pip:
pip install vllm
```

and lets download the model and run model
```python

# Load and run the model:
vllm serve "Ali-Yaser/Qwen3-R1-4B"
```

and Run it this is example
#
```
# Call the server using curl:
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ali-Yaser/Qwen3-R1-4B",
		"messages": [
			{
				"role": "user",
				"content": "1+434x434+10x22=?"
			}
		]
	}'
```