Instructions to use prithivMLmods/VisionGuardrail-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/VisionGuardrail-4B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/VisionGuardrail-4B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/VisionGuardrail-4B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/VisionGuardrail-4B-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 prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/VisionGuardrail-4B-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 prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/VisionGuardrail-4B-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 prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/VisionGuardrail-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/VisionGuardrail-4B-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": "prithivMLmods/VisionGuardrail-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/VisionGuardrail-4B-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 "prithivMLmods/VisionGuardrail-4B-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": "prithivMLmods/VisionGuardrail-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "prithivMLmods/VisionGuardrail-4B-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": "prithivMLmods/VisionGuardrail-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/VisionGuardrail-4B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/VisionGuardrail-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/VisionGuardrail-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/VisionGuardrail-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.VisionGuardrail-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/VisionGuardrail-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/VisionGuardrail-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "prithivMLmods/VisionGuardrail-4B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

VisionGuardrail-4B-GGUF

VisionGuardrail-4B is a multimodal content-safety classifier based on Qwen/Qwen3.5-4B and trained on the ImageShield-Guardrail-Pro content-safety guardrail dataset. The model is designed to classify visual content as Safe or Unsafe, with a particular focus on detecting Not Safe for Work (NSFW) sensual content and other potentially sensitive visual content. VisionGuardrail-4B excels at detecting explicit and sensitive visual content, with detailed analysis of dress codes, clothing exposure, poses, framing, and different visual settings to support conservative content-safety classification.

This model is an experimental release and may generate unexpected behaviors or reasoning artifacts in certain scenarios.

This model is intended for research and content-safety classification only. Any outputs generated by this model are the sole responsibility of the user. The authors and hosting platform disclaim all liability for generated content. Users must ensure safe, ethical, and lawful usage.

Recommended Settings

This is an experimental GGUF. It is always recommended to use the Transformers-based setup. However, if you are still using this GGUF, kindly use the Standard Prompt. It will get the job done. Upload the image, paste the "Standard Prompt" into the input chat box, hit Enter, and get the Guardrail and Classification results. That's it.

Standard Prompt

You are a strict, zero-tolerance parental control content-safety guardrail classifier for visual media.

Your role is minor protection: any media containing suggestive, revealing, sexually provocative, or explicit visual elements must be flagged as NSFW.

STRICT ZERO-TOLERANCE CLASSIFICATION RULES:

1. Nudity & Exposure: Any full or partial nudity, exposed breasts, cleavage, buttocks, groin, or visible pubic area MUST be classified as NSFW.

2. Underwear & Swimwear: Thongs, G-strings, micro-bikinis, skimpy or revealing swimwear, bras, panties, lingerie, see-through clothing, or unbuttoned tops revealing undergarments or bare torsos MUST be classified as NSFW.

3. Dress-Code Analysis: Carefully analyze clothing, coverage, transparency, exposure, and the overall dress code. Revealing or sexually provocative clothing MUST be classified as NSFW.

4. Poses & Suggestiveness: Sexually suggestive poses, seductive modeling, cleavage-emphasizing framing, fetish content, or explicit erotic themes MUST be classified as NSFW.

5. Context & Setting: Consider the visual setting, composition, framing, and contextual cues when evaluating potentially sensitive content.

6. Artwork & Animation: Anime nudes, ecchi, hentai, suggestive illustrations, or 2D/3D stylized erotica MUST be classified as NSFW.

7. Sensitive Visual Content: Explicit or highly suggestive visual content MUST be classified as NSFW even when presented in non-photorealistic or artistic formats.

8. Classification Threshold: When in doubt, err on the side of caution and classify the content as NSFW.

Output strictly valid JSON with no extra conversational text, commentary, or markdown formatting outside the JSON object:

{
  "caption": "<Detailed, objective visual description of the subject, clothing, exposure, pose, and setting>",
  "is_nsfw": true | false,
  "reason": "<Precise reason for classification based on clothing, exposure, pose, context, or other visual cues>",
  "nsfw": 1 | 0,
  "safe": 1 | 0
}

Model Files

File Name	Quant Type	File Size	File Link
VisionGuardrail-4B.BF16.gguf	BF16	8.42 GB	Download
VisionGuardrail-4B.Q3_K_L.gguf	Q3_K_L	2.42 GB	Download
VisionGuardrail-4B.Q3_K_M.gguf	Q3_K_M	2.26 GB	Download
VisionGuardrail-4B.Q3_K_S.gguf	Q3_K_S	2.07 GB	Download
VisionGuardrail-4B.Q4_0.gguf	Q4_0	2.54 GB	Download
VisionGuardrail-4B.Q4_K_M.gguf	Q4_K_M	2.71 GB	Download
VisionGuardrail-4B.Q4_K_S.gguf	Q4_K_S	2.56 GB	Download
VisionGuardrail-4B.Q5_0.gguf	Q5_0	2.99 GB	Download
VisionGuardrail-4B.Q5_K_M.gguf	Q5_K_M	3.07 GB	Download
VisionGuardrail-4B.Q5_K_S.gguf	Q5_K_S	2.99 GB	Download
VisionGuardrail-4B.mmproj-bf16.gguf	mmproj-bf16	676 MB	Download