Instructions to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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 prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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 prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF to start chatting

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-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"

VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF

VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored is a multimodal safety classifier built on top of Qwen/Qwen3.5-4B. The model was trained on a mixture of approximately 10,000 video safety and scene-reasoning samples to analyze video content and classify potentially unsafe content across predefined safety categories. The model is designed to generate a structured DESCRIPTION, EXPLANATION, and GUARDRAIL output, making it suitable for video content filtering, safety evaluation, and multimodal guardrail research.

This model is an experimental release and may generate unexpected classifications or reasoning artifacts in certain scenarios. Safety classifications should be treated as model predictions rather than definitive judgments.

Model Files

File Name	Quant Type	File Size	File Link
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.BF16.gguf	BF16	8.42 GB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.F16.gguf	F16	8.42 GB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q4_K_M.gguf	Q4_K_M	2.71 GB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q5_K_M.gguf	Q5_K_M	3.07 GB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q8_0.gguf	Q8_0	4.48 GB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-bf16.gguf	mmproj-bf16	676 MB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-f16.gguf	mmproj-f16	676 MB	Download
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-q8_0.gguf	mmproj-q8_0	367 MB	Download