fredrezones55/ Qwen3.5-Uncensored-HauhauCS-Aggressive:4b

4,716 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

Details

1 week ago

dd3be4e31ad3 · 3.4GB ·

model
qwen35
·
4.54B
·
Q4_K_M
params
{ "presence_penalty": 1.5, "temperature": 1, "top_k": 20, "top_p": 0.95 }
template
{{ .Prompt }}

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.