---
pipeline_tag: video-text-to-text
library_name: transformers
tags:
- text-generation-inference
- llama-cpp
- reinforcement-learning
- video-text-to-text
- alignment-training
- RLHF
- RFT
- video-understanding
- video-classification
- video-safety
- content-safety
- content-moderation
- safety-classifier
- guardrail
datasets:
- prithivMLmods/OpenVideo-Scene-Reasoning
- PALM-Lab/vid-guard-rlhf-unsafe
license: apache-2.0
language:
- en
base_model:
- prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored
---

# **VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF**

> **VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored** is a multimodal safety classifier built on top of **Qwen/Qwen3.5-9B**. 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.

> [!NOTE]
> 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.

> [!NOTE]
> Use [BF16](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.BF16.gguf) / [FP16](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.F16.gguf) for better reasoning and **safety evaluations**.

## Model Files

   File Name | Quant Type | File Size | File Link |
 |-----------|------------|-----------|-----------|
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.BF16.gguf | BF16 | 17.9 GB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.BF16.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.F16.gguf | F16 | 17.9 GB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.F16.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q4_K_M.gguf | Q4_K_M | 5.63 GB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q4_K_M.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q5_K_M.gguf | Q5_K_M | 6.47 GB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q5_K_M.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q8_0.gguf | Q8_0 | 9.53 GB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.Q8_0.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-bf16.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-f16.gguf | mmproj-f16 | 922 MB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-f16.gguf) |
 | VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-q8_0.gguf | mmproj-q8_0 | 624 MB | [Download](https://huggingface.co/prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF/blob/main/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored.mmproj-q8_0.gguf) |

## llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp