Instructions to use QuantFactory/Datarus-R1-14B-preview-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Datarus-R1-14B-preview-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="QuantFactory/Datarus-R1-14B-preview-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/Datarus-R1-14B-preview-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/Datarus-R1-14B-preview-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Datarus-R1-14B-preview-GGUF",
	filename="Datarus-R1-14B-preview.Q4_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/Datarus-R1-14B-preview-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/Datarus-R1-14B-preview-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/Datarus-R1-14B-preview-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/Datarus-R1-14B-preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

SGLang

How to use QuantFactory/Datarus-R1-14B-preview-GGUF 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 "QuantFactory/Datarus-R1-14B-preview-GGUF" \
    --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": "QuantFactory/Datarus-R1-14B-preview-GGUF",
		"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 "QuantFactory/Datarus-R1-14B-preview-GGUF" \
        --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": "QuantFactory/Datarus-R1-14B-preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/Datarus-R1-14B-preview-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Datarus-R1-14B-preview-GGUF 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 QuantFactory/Datarus-R1-14B-preview-GGUF 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 QuantFactory/Datarus-R1-14B-preview-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Datarus-R1-14B-preview-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Datarus-R1-14B-preview-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Datarus-R1-14B-preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Datarus-R1-14B-preview-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Datarus-R1-14B-preview-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Datarus-R1-14B-preview-GGUF

This is quantized version of DatarusAI/Datarus-R1-14B-preview created using llama.cpp

Original Model Card

Datarus-R1-14B-preview

🚀 Overview

Datarus-R1-14B-Preview is a 14B-parameter open-weights language model fine-tuned from Qwen2.5-14B-Instruct, designed to act as a virtual data analyst and graduate-level problem solver. Unlike traditional models trained on isolated Q&A pairs, Datarus learns from complete analytical trajectories—including reasoning steps, code execution, error traces, self-corrections, and final conclusions—all captured in a ReAct-style notebook format.

Key Highlights

🎯 State-of-the-art efficiency: Surpasses similar-sized models and competes with 32B+ models while using 18-49% fewer tokens
🔄 Dual reasoning interfaces: Supports both Agentic (ReAct) mode for interactive analysis and Reflection (CoT) mode for concise documentation
📊 Superior performance: Achieves up to 30% higher accuracy on AIME 2024/2025 and LiveCodeBench
💡 "AHA-moment" pattern: Exhibits efficient hypothesis refinement in 1-2 iterations, avoiding circular reasoning loops

🔗 Quick Links

🌐 Website: https://datarus.ai
💬 Try the Demo: https://chat.datarus.ai
🛠️ Jupyter Agent: GitHub Repository
📄 Paper: Datarus-R1: An Adaptive Multi-Step Reasoning LLM

📊 Performance

Benchmark Results

Benchmark	Datarus-R1-14B-Preview	QwQ-32B	Phi-4-reasoning	DeepSeek-R1-Distill-14B
LiveCodeBench v6	57.7	56.6	52.6	48.6
AIME 2024	70.1	76.2	74.6*	-
AIME 2025	66.2	66.2	63.1*	-
GPQA Diamond	62.1	60.1	55.0	58.6

*Reported values from official papers

Token Efficiency and Performance

🎯 Model Card

Model Details

Model Type: Language Model for Reasoning and Data Analysis
Parameters: 14.8B
Training Data: 144,000 synthetic analytical trajectories across finance, medicine, numerical analysis, and other quantitative domains + A curated collection of reasoning datasets.
Language: English
License: Apache 2.0

Intended Use

Primary Use Cases

Data Analysis: Automated data exploration, statistical analysis, and visualization
Mathematical Problem Solving: Graduate-level mathematics including AIME-level problems
Code Generation: Creating analytical scripts and solving programming challenges
Scientific Reasoning: Complex problem-solving in physics, chemistry, and other sciences
Interactive Notebooks: Building complete analysis notebooks with iterative refinement

Dual Mode Usage

Agentic Mode (for interactive analysis)

Use <step>, <thought>, <action>, <action_input>, <observation> tags
Enables iterative code execution and refinement
Best for data analysis, simulations, and exploratory tasks

Reflection Mode (for documentation)

Use <think> and <answer> tags
Produces compact, self-contained reasoning chains
Best for mathematical proofs, explanations, and reports

📚 Citation

@article{benchaliah2025datarus,
  title={Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis},
  author={Ben Chaliah, Ayoub and Dellagi, Hela},
  journal={arXiv preprint arXiv:2508.13382},
  year={2025}
}

🤝 Contributing

We welcome contributions! Please see our GitHub repository for:

Bug reports and feature requests
Pull requests
Discussion forums

📄 License

This model is released under the Apache 2.0 License.

🙏 Acknowledgments

We thank the Qwen team for the excellent base model and the open-source community for their valuable contributions.

📧 Contact

Email: ayoub1benchaliah@gmail.com, hela.dellagi@outlook.com
Website: https://datarus.ai
Demo: https://chat.datarus.ai

Experience the future of AI-powered data analysis with Datarus-R1

Try Demo | View Code | Read Paper

⭐ Support

If you find this model and Agent pipeline useful, please consider Like/Star! Your support helps us continue improving the project.

Found a bug or have a feature request? Please open an issue on GitHub.

Made with ❤️ by the Datarus Team from Paris

Downloads last month: 25

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/Datarus-R1-14B-preview-GGUF

Base model

Qwen/Qwen2.5-14B

Quantized

(77)

this model

Paper for QuantFactory/Datarus-R1-14B-preview-GGUF

Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis

Paper • 2508.13382 • Published Aug 18, 2025 • 15