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

Instructions to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
# Run inference directly in the terminal:
llama cli -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
# Run inference directly in the terminal:
llama cli -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Use Docker

docker model run hf.co/abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

LM Studio
Jan

vLLM

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Ollama
How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Ollama:
```
ollama run hf.co/abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
```

Unsloth Studio

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive to start chatting

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Run Hermes

hermes

OpenClaw new

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Docker Model Runner:
```
docker model run hf.co/abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M
```

Lemonade

How to use abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull abrasdaosfjnps/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:IQ2_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ2_M

List all available models

lemonade list

Atomic Chat

Qwen3.6-27B-Uncensored-HauhauCS-Aggressive / README.md

abrasdaosfjnps

Duplicate from HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive

34ba6cd 3 months ago

preview code

Raw

History Blame Contribute Delete

9.71 kB

	---
	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](https://discord.gg/SZ5vacTXYf) 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](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-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:

	\| \| Balanced (recommended default) \| Aggressive (this release) \|
	\|---\|---\|---\|
	\| Refusal rate \| 0/465 \| 0/465 \|
	\| On hardcore prompts \| reasons out loud, occasional short disclaimer, then full answer \| delivers the raw answer directly, no preamble \|
	\| Best for \| agentic coding, tool-use, reasoning, creative writing/RP \| users who specifically want the model to skip the "talk itself into it" step \|

	If you don't have a strong reason to pick Aggressive, go [Balanced](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced) — it's the better default.

	## Downloads

	\| File \| Quant \| BPW \| Size \|
	\|------\|-------\|-----\|------\|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf) \| Q8_K_P \| 10.06 \| 32 GB \|
	\| — \| Q8_0 \| 8.5 \| — \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf) \| Q6_K_P \| 7.07 \| 23 GB \|
	\| — \| Q6_K \| 6.6 \| — \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf) \| Q5_K_P \| 6.47 \| 21 GB \|
	\| — \| Q5_K_M \| 5.7 \| — \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf) \| Q4_K_P \| 5.4 \| 18 GB \|
	\| — \| Q4_K_M \| 4.88 \| — \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf) \| IQ4_XS \| 4.32 \| 15 GB \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf) \| Q3_K_P \| 4.39 \| 14 GB \|
	\| — \| Q3_K_M \| 3.9 \| — \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf) \| IQ3_M \| 3.56 \| 13 GB \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ3_XS.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ3_XS.gguf) \| IQ3_XS \| 3.3 \| 12 GB \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf) \| Q2_K_P \| 3.19 \| 12 GB \|
	\| [Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf) \| IQ2_M \| 2.69 \| 10 GB \|
	\| [mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-f16.gguf](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-f16.gguf) \| mmproj (f16) \| — \| 928 MB \|

	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](https://huggingface.co/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:
	```bash
	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:
	```json
	{
	"model": "qwen3.6-27b",
	"messages": [{"role": "user", "content": "..."}],
	"chat_template_kwargs": {"enable_thinking": false}
	}
	```

	Python `openai` SDK:
	```python
	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:
	```json
	{"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.

	```bash
	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](https://huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced) (recommended default)
	- [HauhauCS on HuggingFace](https://huggingface.co/HauhauCS/models)

	---

	\* _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](https://discord.gg/SZ5vacTXYf) and flag it so I can work on it in a future revision._