license: apache-2.0
tags:

• uncensored
• qwen3.6
• gguf
• vision
• multimodal
  language:
• en
• zh
• multilingual
  pipeline_tag: image-text-to-text
  base_model: Qwen/Qwen3.6-27B

Qwen3.6-27B-Uncensored-HauhauCS-Aggressive

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

Qwen3.6-27B uncensored by HauhauCS. 0/465 Refusals. *

Not sure which variant to pick? 99.9%+ of users should use Balanced — same 0/465 refusal rate, more stable sampling, great for agentic coding / tool-use / reasoning / creative writing. Pick Aggressive only if you specifically want the model to skip its preamble on hardcore prompts.

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 to Files and versions to see all available downloads.

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

Both variants hit 0/465 refusals on the benchmark. Same capability, same uncensoring outcome. The difference is how they deliver on edgy prompts:

If you don't have a strong reason to pick Aggressive, go Balanced — it's the better default.

Downloads

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

What 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.

Specs

• 27B dense parameters
• 64 layers, layout: 16 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
• 48 linear attention layers + 16 full gated-attention layers
• Gated DeltaNet: 48 V heads / 16 QK heads, head dim 128
• Gated Attention: 24 Q heads / 4 KV heads, head dim 256, rope dim 64
• Hidden dim 5120, FFN dim 17408, vocab 248320
• 262K native context, extensible to ~1M with YaRN
• Natively multimodal (text, image, video) — ships with mmproj
• Based on Qwen/Qwen3.6-27B

Recommended Settings

From the official Qwen authors:

Thinking mode (default) — general tasks:

• temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Thinking mode — precise coding / WebDev:

• temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Non-thinking (Instruct) mode:

• temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

My personal preference: I run presence_penalty=1.5 even in thinking mode. Both values work, but with the official 0.0 it can think a lot more than it needs to. Bumping it to 1.5 reins that in without hurting output quality. Your call — try both.

Important:

• Keep at least 128K context to preserve thinking capabilities
• Recommended output length: 32,768 tokens for most queries, up to 81,920 for competition-tier math/code
• Use --jinja with llama.cpp for proper chat template handling
• Vision support requires the mmproj file alongside the main GGUF
• YaRN rope scaling is static in llama.cpp and can hurt short-context performance — only modify rope_parameters if you actually need >262K context

Prompting tip: this model is a bit more sensitive to prompt clarity than Qwen3.5-35B-A3B. Spell out format, constraints, and scope — it'll stay on rails much better than with vague instructions.

Turning Thinking On/Off

Qwen3.6 ships with thinking on by default. Turn it off when you want faster, shorter replies and don't need chain-of-thought.

Heads up: Qwen3.6 does not support the /think and /no_think soft switches that Qwen3 had. You must use the chat-template kwarg below.

LM Studio

1. Load the model
2. Right-side settings panel → Model Settings → Prompt Template (or Chat Template Options)
3. Set enable_thinking to false in the template kwargs
4. Some LM Studio versions expose this as a direct "Reasoning" / "Thinking" toggle — same effect

llama.cpp

llama-server — set as default for all requests:

llama-server -m Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
  --mmproj mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99 \
  --chat-template-kwargs '{"enable_thinking": false}'

Per-request via the OpenAI-compatible API:

{
  "model": "qwen3.6-27b",
  "messages": [{"role": "user", "content": "..."}],
  "chat_template_kwargs": {"enable_thinking": false}
}

Python openai SDK:

client.chat.completions.create(
    model="qwen3.6-27b",
    messages=[{"role": "user", "content": "..."}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)

Agent scenarios — keep reasoning in context across turns:

{"chat_template_kwargs": {"preserve_thinking": true}}

This retains the reasoning block in chat history. Useful for agents where reasoning consistency across tool-call loops matters.

Usage

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

llama-cli -m Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
  --mmproj mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99

Other Models

• Balanced variant (recommended default)
• HauhauCS on HuggingFace

* Tested with both automated and manual refusal benchmarks — none found. If you hit one that's actually obstructive to your use case, join the Discord and flag it so I can work on it in a future revision.