Instructions to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="studio409/YuFeng-XGuard-Reason-0.6B-GGUF",
	filename="YuFeng-XGuard-Reason-0.6B.f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

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 studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

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 studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

Use Docker

docker model run hf.co/studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

LM Studio
Jan

vLLM

How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "studio409/YuFeng-XGuard-Reason-0.6B-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": "studio409/YuFeng-XGuard-Reason-0.6B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

Ollama
How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with Ollama:
```
ollama run hf.co/studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
```

Unsloth Studio

How to use studio409/YuFeng-XGuard-Reason-0.6B-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 studio409/YuFeng-XGuard-Reason-0.6B-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 studio409/YuFeng-XGuard-Reason-0.6B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for studio409/YuFeng-XGuard-Reason-0.6B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with Docker Model Runner:
```
docker model run hf.co/studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16
```

Lemonade

How to use studio409/YuFeng-XGuard-Reason-0.6B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull studio409/YuFeng-XGuard-Reason-0.6B-GGUF:F16

Run and chat with the model

lemonade run user.YuFeng-XGuard-Reason-0.6B-GGUF-F16

List all available models

lemonade list

YuFeng XGuard Reason 0.6B GGUF

This repository provides a GGUF-format distribution of Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B for local GGML-based inference runtimes.

The model is intended for text safety review and content risk analysis. It is not a guarantee of correctness: downstream applications should treat the output as a risk signal and combine it with product policy, user confirmation, logging, and human review when required.

File

File	Description
`YuFeng-XGuard-Reason-0.6B.f16.gguf`	F16 GGUF model for YuFeng XGuard Reason 0.6B

Source

The upstream model is:

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B: https://huggingface.co/Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

The upstream model card identifies the model as Apache-2.0 licensed and based on Qwen/Qwen3-0.6B.

Download

hf download studio409/YuFeng-XGuard-Reason-0.6B-GGUF \
  YuFeng-XGuard-Reason-0.6B.f16.gguf \
  --repo-type model \
  --local-dir yufeng_xguard_reason_0_6b_gguf

Intended Use

This model can be used to review text prompts, generated text, subtitles, or other text fields for safety risks. Actual moderation categories, decision thresholds, and enforcement behavior depend on the application runtime and policy layer.

License

The upstream model is distributed under the Apache License 2.0. This GGUF distribution follows the same license notice.

Please review the upstream model and license before use or redistribution:

https://huggingface.co/Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

Disclaimer

This is an unofficial GGUF-format distribution. YuFeng XGuard Reason, Qwen, and related upstream artifacts belong to their respective authors. This repository is provided for model-format compatibility and local inference convenience.

Downloads last month: 106

GGUF

Model size

0.8B params

Architecture

qwen3

Hardware compatibility

16-bit

Model tree for studio409/YuFeng-XGuard-Reason-0.6B-GGUF

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

Quantized

(3)

this model