HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive · Hugging Face

Source: https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#qwen36-35b-a3b-uncensored-hauhaucs-aggressiveQwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

**Join the Discord**for updates, roadmaps, projects, or just to chat.

Qwen3.6-35B-A3B uncensored by HauhauCS.0/465 Refusals.

HuggingFace’s “Hardware Compatibility” widget doesn’t recognize K_P quants— it may show fewer files than actually exist. Click**“View +X variants”or go toFiles and versions**to see all available downloads.

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#aboutAbout

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.

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#aggressive-variantAggressive Variant

Stronger uncensoring — model is fully unlocked and won’t refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.

For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it’s available.

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#downloadsDownloads

All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#what-are-k_p-quantsWhat are K_P quants?

K_P (“Perfect”) quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.

A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.

**Note:**K_P quants may show as “?” in LM Studio’s quant column. This is a display issue only — the model loads and runs fine.

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#specsSpecs

• 35B total parameters, ~3B active per forward pass (MoE)
• 256 experts, 8 routed per token
• Hybrid architecture: linear attention + full softmax attention (3:1 ratio)
• 40 layers
• 262K native context
• Natively multimodal (text, image, video)
• Based onQwen/Qwen3.6-35B-A3B

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#recommended-settingsRecommended Settings

From the official Qwen authors:

Thinking mode (default):

• General:temperature=1\.0, top\_p=0\.95, top\_k=20, min\_p=0, presence\_penalty=1\.5
• Coding/precise tasks:temperature=0\.6, top\_p=0\.95, top\_k=20, min\_p=0, presence\_penalty=0

Non-thinking mode:

• General:temperature=0\.7, top\_p=0\.8, top\_k=20, min\_p=0, presence\_penalty=1\.5
• Reasoning tasks:temperature=1\.0, top\_p=1\.0, top\_k=40, min\_p=0, presence\_penalty=2\.0

Important:

• Keep at least 128K context to preserve thinking capabilities
• Use\-\-jinjaflag with llama.cpp for proper chat template handling
• Vision support requires themmprojfile alongside the main GGUF

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#usageUsage

Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.

llama-cli -m Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
  --mmproj mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99

https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive#other-modelsOther Models

• HauhauCS on HuggingFace