C/C++ — https://github.com/ggml-org/llama.cpp
Open-weight model · Video text to text
VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF
by Prithiv Sakthi prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF
C/C++ — https://github.com/ggml-org/llama.cpp
Parameters—
Context—
Weights28.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.5k
Model Card
By Prithiv Sakthi, published under apache-2.0, revision f2545b42fc30.
C/C++ — https://github.com/ggml-org/llama.cpp
Read Prithiv Sakthi's full model card
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.
[!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.
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 |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Identity and Version
- Repository
- prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF
- Publisher
- Prithiv Sakthi
- Task
- Video text to text
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- f2545b42fc30b58897d999a14aa2c798e5e46529
- First published
- 2026-08-10
- Last updated
- 2026-08-11
Files and Weights
10 files, 28.8 GB in total. The weights are 8 files totalling 28.8 GB in gguf.
Weights8 files · 28.8 GB
Documentation1 file · 3.5 KB
Repository1 file · 2.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.BF16.gguf | Weights | 8.4 GB | bf372073dfcd |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.F16.gguf | Weights | 8.4 GB | 2ec93c4d515f |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q4_K_M.gguf | Weights | 2.7 GB | 17222edd7a44 |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q5_K_M.gguf | Weights | 3.1 GB | 29fca37db4dd |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.Q8_0.gguf | Weights | 4.5 GB | eaeed8975068 |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-bf16.gguf | Weights | 675.6 MB | 44b9b07be9ba |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-f16.gguf | Weights | 675.6 MB | 44b9b07be9ba |
| VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored.mmproj-q8_0.gguf | Weights | 366.9 MB | afc2e211dff2 |
| README.md | Documentation | 3.5 KB | — |
| .gitattributes | Repository | 2.3 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 28.8 GB
Download from Prithiv Sakthi
Released by Prithiv Sakthi through its official repository on Hugging Face. Read the license.
Built From
- Derived from prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored
- Quantized from prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored
- Trained on (disclosed) PALM-Lab/vid-guard-rlhf-unsafe
- Trained on (disclosed) prithivMLmods/OpenVideo-Scene-Reasoning
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 28.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF
Can I use VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF commercially?
Yes. VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models