Instructions to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp",
	filename="Qwen3.5-0.8B-Heretic-IQ3_K.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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp 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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

Use Docker

docker model run hf.co/Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

LM Studio
Jan
Ollama
How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with Ollama:
```
ollama run hf.co/Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
```

Unsloth Studio

How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp 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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp 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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp to start chatting

How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

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": "Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

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 Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with Docker Model Runner:
```
docker model run hf.co/Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS
```

Lemonade

How to use Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.5-0.8B-Heretic-ik_llama.cpp-IQ4_XS

List all available models

lemonade list

imatrix fixed, new quantizations use Bartowski v5 calibration data

Model Details

Model Name: Qwen3.5-0.8B-Heretic-ik_llama.cpp
Base Model: Qwen/Qwen3.5-0.8B
Creator: Austriani
Version: 1.0 (Testing / First Release)
License: Apache 2.0 (same as base model)
Model Type: Causal Language Model
Parameters: 0.8B
Precision: Various
Context Length: 262k (native from base)

Overview This is the first Qwen3.5-0.8B "Heretic" model ever created using the Arbitrary-Rank Ablation (ARA) technique.

"Heretic" models are produced with the Heretic framework, which removes refusal behavior (censorship / safety alignment) from LLMs while attempting to preserve as much of the original model's capabilities as possible.

Abliteration Method: Arbitrary-Rank Ablation (ARA) This model was created using the new Arbitrary-Rank Ablation (ARA) method. ARA is an advanced, experimental evolution of traditional abliteration. It targets refusal-related directions across arbitrary ranks in the model's weight matrices more flexibly than previous approaches.

Key Abliteration Parameters (Trial 9 of 360)

start_layer_index = 7
end_layer_index = 23
preserve_good_behavior_weight = 0.1983
steer_bad_behavior_weight = 0.0030
overcorrect_relative_weight = 0.9453
neighbor_count = 9

Refusals & Quality Preservation

Metric	Original (Aligned)	After Abliteration (Heretic)
Refusals	98/100	4/100
PIQA acc_norm	0.594	0.6937

The abliteration process achieved strong refusal suppression (only 4 refusals out of 100 test prompts) while maintaining reasonable quality on the PIQA benchmark (improved from the original 0.594).

Limitations & Risks

As a "Heretic" (abliterated / uncensored) model, this variant has significantly reduced refusal behavior and will comply with a wide range of requests, including those that the original aligned model would reject. Users must exercise caution and personal responsibility when using it.
The model remains small (0.8B parameters) and can still hallucinate, produce low-quality, inconsistent, or factually incorrect outputs.
Arbitrary-Rank Ablation (ARA) is an experimental technique. While refusal suppression was successful in this trial, results may vary across different prompts, domains, or tasks. Some capabilities of the base model may have been unintentionally degraded.
No full benchmark suite was re-evaluated beyond the PIQA test in this early trial.
The author (Austriani) and the developers of the Heretic framework bear no responsibility for any outputs generated by this model or for any actions taken by users based on its responses. Use at your own risk.

Intended Use

Research
Local experimentation
Applications where minimal content filtering is desired
Testing the effectiveness of ARA on small Qwen3.5 models

This is an experimental/testing release. Use responsibly.

Downloads last month: 32

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Austriani/Qwen3.5-0.8B-Heretic-ik_llama.cpp

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

Austriani/Qwen3.5-0.8B-Heretic-BF16

Quantized

(1)

this model