Instructions to use Chan-Y/TurkishReasoner-Qwen2.5-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chan-Y/TurkishReasoner-Qwen2.5-3B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Chan-Y/TurkishReasoner-Qwen2.5-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Chan-Y/TurkishReasoner-Qwen2.5-3B")
model = AutoModelForCausalLM.from_pretrained("Chan-Y/TurkishReasoner-Qwen2.5-3B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Chan-Y/TurkishReasoner-Qwen2.5-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chan-Y/TurkishReasoner-Qwen2.5-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chan-Y/TurkishReasoner-Qwen2.5-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Chan-Y/TurkishReasoner-Qwen2.5-3B

SGLang

How to use Chan-Y/TurkishReasoner-Qwen2.5-3B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Chan-Y/TurkishReasoner-Qwen2.5-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chan-Y/TurkishReasoner-Qwen2.5-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Chan-Y/TurkishReasoner-Qwen2.5-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chan-Y/TurkishReasoner-Qwen2.5-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Chan-Y/TurkishReasoner-Qwen2.5-3B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Chan-Y/TurkishReasoner-Qwen2.5-3B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Chan-Y/TurkishReasoner-Qwen2.5-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Chan-Y/TurkishReasoner-Qwen2.5-3B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Chan-Y/TurkishReasoner-Qwen2.5-3B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Chan-Y/TurkishReasoner-Qwen2.5-3B with Docker Model Runner:
```
docker model run hf.co/Chan-Y/TurkishReasoner-Qwen2.5-3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

TurkishReasoner-Qwen2.5-3B

Model Description

TurkishReasoner-Qwen2.5-3B is a mid-sized Turkish reasoning model built on Qwen's efficient Qwen2.5-3B foundation. This model provides an excellent balance between performance and computational efficiency, delivering structured reasoning capabilities in Turkish while requiring moderate resources for deployment.

Key Features

Built on Qwen's efficient 3B parameter architecture
Specialized for Turkish reasoning with structured output format
Excellent balance between performance and resource requirements
Strong support for structured data and structured outputs
Enhanced instruction following for reasoning tasks
Support for multilingual context with Turkish optimization

Technical Specifications

Base Model: Qwen/Qwen2.5-3B
Parameters: 3.09 billion
Input: Text
Hardware Requirements: ~8GB VRAM
Training Infrastructure: NVIDIA T4 GPU

Usage

This model is ideal for applications requiring solid reasoning in Turkish with moderate computational resources:

Educational applications requiring detailed problem-solving
Mid-tier deployment environments with limited GPU resources
Applications balancing reasoning quality with efficiency requirements
Development and prototyping of reasoning-intensive applications

Example Usage

from transformers import pipeline

pipe = pipeline("text-generation", model="Chan-Y/TurkishReasoner-Qwen2.5-3B", device=0)

messages = [
    {"role": "system", "content": """Sen kullanıcıların isteklerine Türkçe cevap veren bir asistansın ve sana bir problem verildi.
Problem hakkında düşün ve çalışmanı göster.
Çalışmanı <start_working_out> ve <end_working_out> arasına yerleştir.
Sonra, çözümünü <SOLUTION> ve </SOLUTION> arasına yerleştir.
Lütfen SADECE Türkçe kullan."""},
    {"role": "user", "content": "121'in karekökü kaçtır?"},
]

response = pipe(messages)
print(response)

For more information or assistance with this model, please contact the developers:

Cihan Yalçın: https://www.linkedin.com/in/chanyalcin/
Şevval Nur Savcı: https://www.linkedin.com/in/%C5%9Fevval-nur-savc%C4%B1/

Downloads last month: 27

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Chan-Y/TurkishReasoner-Qwen2.5-3B

Quantizations

1 model

Collection including Chan-Y/TurkishReasoner-Qwen2.5-3B

TurkishReasoner

Collection

Models that are trained on reasoning task in Turkish language. • 4 items • Updated Nov 3, 2025 • 1