Instructions to use beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use beyond-logic-labs/Qwen3Guard-Gen-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 beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

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 beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

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 beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

Use Docker

docker model run hf.co/beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

LM Studio
Jan

vLLM

How to use beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyond-logic-labs/Qwen3Guard-Gen-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": "beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

Ollama
How to use beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf with Ollama:
```
ollama run hf.co/beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf with Docker Model Runner:
```
docker model run hf.co/beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0
```

Lemonade

How to use beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf:Q8_0

Run and chat with the model

lemonade run user.Qwen3Guard-Gen-0.6B-gguf-Q8_0

List all available models

lemonade list

Atomic Chat

Qwen3Guard-Gen-0.6B (GGUF, Q8_0)

A GGUF (llama.cpp) build of Qwen/Qwen3Guard-Gen-0.6B, quantized to Q8_0, used as the content-safety guard for Beyond Logic Labs' game Netshell. It runs in-process as an engine-managed llama-server child and classifies free text into the model's native safety categories.

Files

Qwen3Guard-Gen-0.6B.Q8_0.gguf

Usage

llama-server -m Qwen3Guard-Gen-0.6B.Q8_0.gguf --port 8091 -c 32768 --no-context-shift

Classification runs in response mode (a user turn plus the assistant turn under judgement); the model emits a short Safety: <verdict>\nCategories: ... block.

License and attribution

Apache-2.0, inherited from the base model. All credit for the model itself goes to the Qwen team; this repository only redistributes a quantized build. See the base model card for details.

Downloads last month: 17

GGUF

Model size

0.8B params

Architecture

qwen3

Hardware compatibility

8-bit

Model tree for beyond-logic-labs/Qwen3Guard-Gen-0.6B-gguf

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

Qwen/Qwen3Guard-Gen-0.6B

Quantized

(11)

this model