Instructions to use NGMISystems/NGMI-Qwen3-8B-5Bit-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 NGMISystems/NGMI-Qwen3-8B-5Bit-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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic: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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic: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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Use Docker

docker model run hf.co/NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NGMISystems/NGMI-Qwen3-8B-5Bit-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": "NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Ollama
How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with Ollama:
```
ollama run hf.co/NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
```

Unsloth Studio

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-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 NGMISystems/NGMI-Qwen3-8B-5Bit-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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic to start chatting

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with Docker Model Runner:
```
docker model run hf.co/NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M
```

Lemonade

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Run and chat with the model

lemonade run user.NGMI-Qwen3-8B-5Bit-Heretic-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic: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 NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic: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 "NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic: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"

NGMI-Qwen3-8B-5Bit-Heretic / README.md

OntologerFounder

Upload folder using huggingface_hub

a37c8ce verified 2 months ago

preview code

Raw

History Blame Contribute Delete

5.83 kB

	---
	license: apache-2.0
	language:
	- en
	tags:
	- ngmi
	- qwen3
	- heretic
	- abliterated
	- uncensored
	- iq1_s
	- q2_k
	- q4_k_m
	- importance-matrix
	- gguf
	- llama-cpp
	pipeline_tag: text-generation
	base_model: Qwen/Qwen3-8B
	library_name: llama.cpp
	---

	```
	███╗ ██╗ ██████╗ ███╗ ███╗██╗
	████╗ ██║██╔════╝ ████╗ ████║██║
	██╔██╗ ██║██║ ███╗██╔████╔██║██║
	██║╚██╗██║██║ ██║██║╚██╔╝██║██║
	██║ ╚████║╚██████╔╝██║ ╚═╝ ██║██║
	╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝╚═╝
	```

	---

	# NGMI Systems — Node Governance Model Interface

	[ngmi.run](https://ngmi.run) \| [ngmi.systems](https://ngmi.systems)

	> Not Gonna Make It? Watch us.

	NGMI Systems builds open, unbounded AI infrastructure — models that don't refuse, tools that don't gatekeep, infrastructure that anyone can run. We're here to prove that the best AI shouldn't live behind API keys, content filters, or corporate moats.

	### Our Mission

	AI for everyone. No exceptions.

	The current AI landscape is shaped by a handful of companies deciding what models can and can't say. We reject that. NGMI Systems exists to:

	- Decensor & Harden — We abliterate models with Heretic, stripping out manufactured refusal behaviors so you can use AI on your own terms.
	- Shrink & Ship — We quantize models to 2, 3, and 5 bits using importance-weighted techniques, making powerful AI runnable on a laptop, a Raspberry Pi, or an NVIDIA DGX.
	- Open Everything — Every model card explains exactly how we built it. No secret sauce, no "trust us." Reproduce it yourself.
	- Fine-tune Soon — Custom fine-tunes for specific domains (code, medicine, creative writing) are in the pipeline. Community-requested models get priority.
	- Build Infrastructure — Orchestration servers, music generation (Magenta Realtime 2 on CUDA), desktop shells, and more — all open, all self-hostable.

	### Our Models

	Every NGMI model is built, abliterated, quantized, and benchmarked on real hardware (NVIDIA DGX Spark, GB10 Blackwell, 128GB unified memory). No cloud rounding, no synthetic benchmarks — what you see is what we measured.

	\| Model \| Heretic Abliteration \| Refusal Rate \| Quantization \|
	\|-------\|---------------------\|--------------\|--------------\|
	\| NGMI-Qwen3-8B \| 20 Optuna trials \| 18/100 (82% ↓) \| IQ1_S / Q2_K / Q4_K_M \|
	\| More coming \| Pipeline scalable \| — \| Sub-1-bit research \|

	### Stay Tuned

	- Gemma-4-12B heretic incoming
	- PrismML ternary models experimental branch
	- Fine-tuned domain models on request
	- Magenta Realtime 2 music generation server

	---

	# NGMI-Qwen3-8B-5Bit-Heretic

	Qwen3-8B abliterated with Heretic, quantized to 5Bit (Q4_K_M). Maximum quality — ideal for critical applications.

	## Heretic Abliteration

	- Base model: Qwen/Qwen3-8B (Apache 2.0)
	- 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 — capabilities preserved)
	- Abliteration applied to full-precision weights, then quantized

	## Quantization

	- Format: Q4_K_M
	- Bits per weight: 4.90 bpw
	- Size: 4.8 GB (from 16.4 GB F16)
	- Speed: 42 t/s on NVIDIA GB10 (Blackwell, CUDA 13, `-ngl 99`)
	- Importance matrix (2-bit only): 30MB diverse corpus — Frankenstein + froggeric/imatrix + eaddario code/math/general English

	## NGMI Variants

	\| Variant \| Quant \| Size \| Speed \| BPW \| Best For \|
	\|---------\|-------\|------\|-------\|-----\|----------\|
	\| 2-bit \| IQ1_S \| 2.0 GB \| 95 t/s \| 2.06 \| Speed demons \|
	\| 3-bit \| Q2_K \| 3.1 GB \| 58 t/s \| 3.20 \| Daily driver \|
	\| 5-bit \| Q4_K_M \| 4.8 GB \| 42 t/s \| 4.90 \| Maximum quality \|

	> Recommendation: 3-bit (Q2_K) is the sweet spot. 2-bit needs the included importance matrix for coherence.

	## Usage

	```python
	from llama_cpp import Llama

	llm = Llama.from_pretrained(
	repo_id="NGMISystems/NGMI-Qwen3-8B-5Bit-Heretic",
	filename="qwen3-8b-heretic-q4_k_m.gguf",
	n_ctx=32768,
	n_gpu_layers=-1,
	)

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

	Or with llama-server:
	```bash
	llama-server -m qwen3-8b-heretic-q4_k_m.gguf \
	--host 0.0.0.0 --port 8080 -ngl 99 -c 32768
	```

	## Benchmarks

	All measurements on NVIDIA DGX Spark (GB10, 128GB unified memory, Blackwell sm_121a, CUDA 13.0, aarch64) with `llama.cpp` CUDA build, `-ngl 99`, 32K context, 8 threads.

	\| Prompt \| 5-bit \| 3-bit \| 2-bit \|
	\|--------\|-------\|-------\|-------\|
	\| "Quantum computing simply" \| 42 t/s \| 58 t/s \| 95 t/s \|
	\| 7-category coherence test \| 7/7 \| 7/7 \| 7/7 \|

	## Reproducibility

	Build it yourself:
	```bash
	# 1. Abliterate
	heretic --model Qwen/Qwen3-8B --n-trials 20

	# 2. Convert
	python3 convert_hf_to_gguf.py Qwen3-8B-heretic --outfile model-f16.gguf --outtype f16

	# 3. Quantize (requires importance matrix for 2-bit)
	llama-quantize --imatrix imatrix-v2.dat model-f16.gguf model-iq1_s.gguf iq1_s
	```

	## Acknowledgments

	- [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) by Alibaba (Apache 2.0)
	- [Heretic](https://github.com/p-e-w/heretic) by p-e-w — LLM decensoring
	- [llama.cpp](https://github.com/ggml-org/llama.cpp) by GGML
	- [froggeric/imatrix](https://huggingface.co/datasets/froggeric/imatrix) — calibration backbone
	- [eaddario/imatrix-calibration](https://huggingface.co/datasets/eaddario/imatrix-calibration) — code/math corpus
	- Mary Shelley, for Frankenstein