fredrezones55/ Qwen3.5-Uncensored-HauhauCS-Aggressive

4,704 1 week ago

Monolith GGUF of HauhauCS' Qwen3.5-Uncensored-Aggressive model family. With full vision support, patched model.

vision tools thinking 4b 9b 
ollama run fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b

Applications

Claude Code
Claude Code ollama launch claude --model fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
Codex
Codex ollama launch codex --model fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
OpenCode
OpenCode ollama launch opencode --model fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
OpenClaw
OpenClaw ollama launch openclaw --model fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b

Models

View all →

3 models

Qwen3.5-Uncensored-HauhauCS-Aggressive:4b

3.4GB · 256K context window · Text, Image · 1 week ago

Qwen3.5-Uncensored-HauhauCS-Aggressive:9b

6.5GB · 256K context window · Text, Image · 1 week ago

Readme

I’ll have the other model sizes here in time fully working, my internet is kinda slow…

Qwen3.5 uncensored by HauhauCS.

About

0/465 refusals. Fully uncensored with zero capability loss.

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 Variant

Stronger uncensoring with more thorough refusal removal. If this variant is too loose for your use case, a Balanced variant may follow.

Note: The model is fully unlocked and will not refuse prompts. However, it may occasionally append a short disclaimer at the end of a response (e.g. “This is general information, not legal advice…”). This is baked into the base model’s training and not a refusal — the actual content is still generated in full.

Vision support: This model is natively multimodal. This model has been patched to use Ollama’s native Qwen3.5 vision functionality. full complete quant parity was not a priority.