Instructions to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF 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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

Ollama
How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with Ollama:
```
ollama run hf.co/Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
```

Unsloth Studio

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF 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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF 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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF to start chatting

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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": "Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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 "Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M
```

Lemonade

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Huihui-Qwen3.5-9B-abliterated-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_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 Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Huihui-Qwen3.5-9B-abliterated GGUF

This repository contains GGUF quantized versions of huihui-ai/Huihui-Qwen3.5-9B-abliterated, converted using llama.cpp.

Model Lineage

Qwen/Qwen3.5-9B-Base (Alibaba)
    └── Qwen/Qwen3.5-9B (Alibaba) — Instruct fine-tune
        └── huihui-ai/Huihui-Qwen3.5-9B-abliterated (huihui-ai) — Abliteration via remove-refusals-with-transformers
            └── This GGUF repository (Kausik-A) — llama.cpp quantization

This is an uncensored version of Qwen/Qwen3.5-9B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Model Info

Architecture: Qwen3.5 (32 layers, 4096 hidden size, 16 attention heads, 4 KV heads, 248,320 vocab size)
Context Length: 262,144 tokens
Original Size: ~17GB (F16)

Available Quantizations

File	Type	Size
`Huihui-Qwen3.5-9B-Q3_K_S.gguf`	Q3_K_S	4.0GB
`Huihui-Qwen3.5-9B-Q3_K_M.gguf`	Q3_K_M	4.4GB
`Huihui-Qwen3.5-9B-Q4_0.gguf`	Q4_0	5.0GB
`Huihui-Qwen3.5-9B-Q4_K_S.gguf`	Q4_K_S	5.0GB
`Huihui-Qwen3.5-9B-Q4_K_M.gguf`	Q4_K_M	5.3GB
`Huihui-Qwen3.5-9B-Q5_K_S.gguf`	Q5_K_S	5.9GB
`Huihui-Qwen3.5-9B-Q5_K_M.gguf`	Q5_K_M	6.1GB
`Huihui-Qwen3.5-9B-Q6_K.gguf`	Q6_K	6.9GB
`Huihui-Qwen3.5-9B-Q8_0.gguf`	Q8_0	8.9GB
`Huihui-Qwen3.5-9B-F16.gguf`	F16	17GB

Usage

llama-cli

llama-cli -m Huihui-Qwen3.5-9B-Q4_K_M.gguf -p "Hello, how are you?" -n 512

Ollama

Please use the latest version of ollama v0.17.7.

ollama run huihui_ai/qwen3.5-abliterated:9b

LM Studio

Simply drag and drop the GGUF file into LM Studio.

⚠️ Usage Warnings

Risk of Sensitive or Controversial Outputs: This model's safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model's outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

License

Apache 2.0 — same license as the base Qwen3.5-9B model.

Credits

Component	Author	Link
Base model (Qwen3.5-9B)	Alibaba	Qwen/Qwen3.5-9B
Abliteration	huihui-ai	huihui-ai/Huihui-Qwen3.5-9B-abliterated
Abliteration tool	Sumandora	remove-refusals-with-transformers
Quantization framework	ggerganov	llama.cpp

Downloads last month: 2,716

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Kausik-A/Huihui-Qwen3.5-9B-abliterated-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

huihui-ai/Huihui-Qwen3.5-9B-abliterated

Quantized

(16)

this model