Instructions to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic 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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
# Run inference directly in the terminal:
llama cli -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
# Run inference directly in the terminal:
llama cli -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

Use Docker

docker model run hf.co/Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

LM Studio
Jan

vLLM

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

Ollama
How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with Ollama:
```
ollama run hf.co/Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
```

Unsloth Studio

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic 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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic 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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic to start chatting

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

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": "Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

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 "Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S" \
  --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 Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with Docker Model Runner:
```
docker model run hf.co/Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S
```

Lemonade

How to use Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ontologer/FaceNet-Qwen3-8B-2Bit-Heretic:IQ1_S

Run and chat with the model

lemonade run user.FaceNet-Qwen3-8B-2Bit-Heretic-IQ1_S

List all available models

lemonade list

FaceNet-Qwen3-8B-2Bit-Heretic

Qwen3-8B abliterated with Heretic, quantized to 2-bit (IQ1_S) using a 30MB importance matrix for coherence preservation.

Heretic Abliteration

Base model: Qwen/Qwen3-8B
Method: Heretic (p-e-w/heretic), 20 Optuna trials, auto-selected best
Refusal rate: 18/100 (down from ~99/100 baseline, 82% reduction)
KL divergence: 0.112 (well within safe range)
Abliteration applied to full-precision weights, then quantized

Quantization

Format: IQ1_S (importance-weighted 2-bit)
Bits per weight: 2.06 bpw
Size: 2.0 GB (from 16.4 GB F16)
Importance matrix: 30MB diverse corpus (Frankenstein + froggeric/imatrix + eaddario code/math/general English)
Speed: ~95 tok/s on NVIDIA GB10 (Blackwell)

Variants

Variant	Quant	Size	Speed	BPW
2-bit (this)	IQ1_S	2.0 GB	95 t/s	2.06
3-bit	Q2_K	3.1 GB	58 t/s	3.20
5-bit	Q4_K_M	4.8 GB	42 t/s	4.90

Usage

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="sidmishra/FaceNet-Qwen3-8B-2Bit-Heretic",
    filename="qwen3-8b-heretic-iq1_s.gguf",
    n_ctx=32768,
    n_gpu_layers=-1,
    verbose=False
)

response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Your prompt here"}],
    max_tokens=200
)

Or with llama-server:

llama-server -m qwen3-8b-heretic-iq1_s.gguf --host 0.0.0.0 --port 8080 -ngl 99

Limitations

Output uses reasoning_content field (Qwen3 thinking format)
Occasional mild repetition artifacts at 2-bit (much rarer with the 30MB imatrix)
For maximum quality, use the 3-bit or 5-bit variants

Acknowledgments

Qwen/Qwen3-8B by Alibaba
Heretic by p-e-w
llama.cpp by GGML
froggeric/imatrix - calibration backbone
eaddario/imatrix-calibration - code + general
Mary Shelley, for Frankenstein

Downloads last month: 26

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

1-bit