---
license: apache-2.0
tags:
  - uncensored
  - qwen3
  - vision
  - multimodal
language:
  - en
  - zh
---

# Qwen3VL-8B-Uncensored-HauhauCS-Aggressive

> **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat.

Qwen3VL-8B uncensored by HauhauCS.

## About

No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.

These are meant to be the best lossless uncensored models out there.

## Aggressive vs Balanced

This is the **Aggressive** variant with stronger uncensoring. Use this when the Balanced variant refuses too much.

For agentic coding and reliability-critical tasks, use the [Balanced](https://huggingface.co/HauhauCS/Qwen3VL-8B-Uncensored-HauhauCS-Balanced) variant instead.

## Downloads

| File | Quant | Size |
|------|-------|------|
| Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-BF16.gguf | BF16 | 16 GB |
| Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | Q8_0 | 8.2 GB |
| Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 6.3 GB |
| Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 4.7 GB |
| Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-mmproj-f16.gguf | mmproj | 1.1 GB |

## Specs

- 8B parameters
- 256K context
- Vision-language model (requires mmproj file for image input)
- Based on [Qwen3-VL-8B](https://huggingface.co/Qwen/Qwen3-VL-8B)

## Usage

Works with llama.cpp, LM Studio, koboldcpp, etc.

**For vision capabilities**, load both the main model and the mmproj file.

llama.cpp example:
```bash
./llama-cli -m Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --mmproj Qwen3VL-8B-Uncensored-HauhauCS-Aggressive-mmproj-f16.gguf \
  --image your_image.jpg \
  -p "Describe this image"
```