---

datasets:

• prithivMLmods/ImageShield-Guardrail-Multimodal-20K

base_model:

• prithivMLmods/ImageShield-MMCF-2B-vl

license: apache-2.0

library_name: transformers

tags:

• text-generation-inference
• llama-cpp
• qwen3_vl
• image-classification
• content-safety
• content-moderation
• multimodal
• safety-classifier
• guardrail
• ncii-detection
• visual-safety
• multimodal-content-filter
• MMCF

language:

• en

pipeline_tag: image-text-to-text

---

ImageShield-MMCF-2B-vl-GGUF

> ImageShield-MMCF — Multimodal Content Filter is a multimodal content-safety classifier built on top of Qwen/Qwen3-VL-2B-Instruct and trained on the ImageShield-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.

<a href="https://huggingface.co/prithivMLmods/ImageShield-MMCF-2B-vl#example-cards">

<img src="https://img.shields.io/badge/View-Example_Cards-blue?style=for-the-badge" alt="Jump to Examples" />

</a>

> [!NOTE]

> This model is an experimental release and may exhibit unexpected behavior or reasoning artifacts in certain scenarios.

> [!IMPORTANT]

> 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/Inference

> This is an experimental GGUF. It is always recommended to use the Transformers-based setup.

Model Files

File Name | Quant Type | File Size | File Link |

|-----------|------------|-----------|-----------|

| ImageShield-MMCF-2B-vl.BF16.gguf | BF16 | 3.45 GB | Download |

| ImageShield-MMCF-2B-vl.F16.gguf | F16 | 3.45 GB | Download |

| ImageShield-MMCF-2B-vl.Q3_K_L.gguf | Q3_K_L | 1 GB | Download |

| ImageShield-MMCF-2B-vl.Q3_K_M.gguf | Q3_K_M | 940 MB | Download |

| ImageShield-MMCF-2B-vl.Q3_K_S.gguf | Q3_K_S | 867 MB | Download |

| ImageShield-MMCF-2B-vl.Q4_K_M.gguf | Q4_K_M | 1.11 GB | Download |

| ImageShield-MMCF-2B-vl.Q4_K_S.gguf | Q4_K_S | 1.06 GB | Download |

| ImageShield-MMCF-2B-vl.Q5_K_M.gguf | Q5_K_M | 1.26 GB | Download |

| ImageShield-MMCF-2B-vl.Q5_K_S.gguf | Q5_K_S | 1.23 GB | Download |

| ImageShield-MMCF-2B-vl.Q6_K.gguf | Q6_K | 1.42 GB | Download |

| ImageShield-MMCF-2B-vl.Q8_0.gguf | Q8_0 | 1.83 GB | Download |

| ImageShield-MMCF-2B-vl.mmproj-bf16.gguf | mmproj-bf16 | 823 MB | Download |

| ImageShield-MMCF-2B-vl.mmproj-f16.gguf | mmproj-f16 | 823 MB | Download |

| ImageShield-MMCF-2B-vl.mmproj-q8_0.gguf | mmproj-q8_0 | 445 MB | Download |

llama.cpp

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