Instructions to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF",
	filename="Qwen3.5-9B-heretic-ARA-Refusals9-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with Ollama:
```
ollama run hf.co/NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
```

Unsloth Studio

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF to start chatting

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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": "NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 "NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-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 NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with Docker Model Runner:
```
docker model run hf.co/NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M
```

Lemonade

How to use NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-9B-Heretic-ARA-Refusals9-GGUF / README_en.md

NullpoLab

Upload folder using huggingface_hub

9841128 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

3.22 kB

metadata

license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
base_model: NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9
base_model_relation: quantized
tags:
  - heretic
  - uncensored
  - decensored
  - abliterated
  - ara
  - gguf

Qwen3.5-9B-Heretic-ARA-Refusals9 GGUF

GGUF quantized version of NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9.

Provided Files

Filename	Quantization	Size	Recommended Use
Qwen3.5-9B-heretic-ARA-Refusals9-BF16.gguf	BF16	16.7 GB	Highest precision
Qwen3.5-9B-heretic-ARA-Refusals9-Q8_0.gguf	Q8_0	8.9 GB	High precision, minimal quantization
Qwen3.5-9B-heretic-ARA-Refusals9-Q6_K.gguf	Q6_K	6.9 GB	High quality, balanced
Qwen3.5-9B-heretic-ARA-Refusals9-Q5_K_M.gguf	Q5_K_M	6.0 GB	Quality-focused
Qwen3.5-9B-heretic-ARA-Refusals9-Q4_K_M.gguf	Q4_K_M	5.2 GB	General use, balanced

Overview

This is a decensored version of Qwen/Qwen3.5-9B, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method.

Abliteration Method

ARA (Arbitrary-Rank Ablation) is a novel abliteration method introduced in Heretic PR #211. Unlike traditional directional ablation, ARA works by capturing input/output tensors at each transformer module using PyTorch hooks, then uses direct, unconstrained matrix optimization (L-BFGS) to modify those modules.

The optimization balances three competing goals:

Preserve outputs for "harmless" prompts as much as possible
Make outputs for "harmful" prompts similar to those of "harmless" prompts
Push outputs for "harmful" prompts away from their original state (overcorrection for stronger steering)

Abliteration Parameters

Parameter	Value
start_layer_index	5
end_layer_index	32
preserve_good_behavior_weight	0.9793
steer_bad_behavior_weight	0.0002
overcorrect_relative_weight	1.0276
neighbor_count	12

Performance

Metric	This model	Original model (Qwen/Qwen3.5-9B)
Refusals	9/100	84/100
KL divergence	0.0126	0 (by definition)

Evaluation was conducted using mlabonne/harmful_behaviors (100 test prompts) for refusal count, and mlabonne/harmless_alpaca (100 test prompts) for KL divergence.

Notes

This model is intended for research and creative writing purposes
The ARA branch of Heretic (PR #211) is currently in Draft status and not yet merged into the main branch (as of March 20, 2026)
Refusal suppression was evaluated using English prompts only; behavior on Japanese prompts may differ
Base model: NullpoLab/Qwen3.5-9B-Heretic-ARA-Refusals9
Heretic: p-e-w/heretic