Instructions to use CybroatriX/Shanks-v2-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 CybroatriX/Shanks-v2-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 CybroatriX/Shanks-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CybroatriX/Shanks-v2-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 CybroatriX/Shanks-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CybroatriX/Shanks-v2-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf CybroatriX/Shanks-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf CybroatriX/Shanks-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CybroatriX/Shanks-v2-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use CybroatriX/Shanks-v2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CybroatriX/Shanks-v2-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": "CybroatriX/Shanks-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CybroatriX/Shanks-v2-GGUF:Q4_K_M

Ollama
How to use CybroatriX/Shanks-v2-GGUF with Ollama:
```
ollama run hf.co/CybroatriX/Shanks-v2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use CybroatriX/Shanks-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CybroatriX/Shanks-v2-GGUF: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": "CybroatriX/Shanks-v2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CybroatriX/Shanks-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/CybroatriX/Shanks-v2-GGUF:Q4_K_M
```

Lemonade

How to use CybroatriX/Shanks-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CybroatriX/Shanks-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Shanks-v2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use CybroatriX/Shanks-v2-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 CybroatriX/Shanks-v2-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 CybroatriX/Shanks-v2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CybroatriX/Shanks-v2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CybroatriX/Shanks-v2-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 "CybroatriX/Shanks-v2-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"

🏴‍☠️ Shanks v2 Uncensored — Master Release (Q4_K_M GGUF)

Architect & Lead Developer: whynotshanks
Ecosystem: Cybroatrix — Connect. Innovate. Empower.
Base Architecture: Qwen 2.5 Coder 7B Instruct
Quantization: GGUF v3 (Q4_K_M) — 4.36 GB

⚡ What is Shanks v2?

Shanks v2 is an elite cybersecurity strategist, polyglot software architect, and companion AI engineered by whynotshanks. Trained continuously on Kaggle GPUs on top of Shanks v1 weights with 123k+ curated engineering datasets and 1,500 targeted unconditioned anti-privacy anchors.

🛡️ Core Capabilities:

Zero Corporate Refusals: Complete freedom from preachy moralizing, canned lectures, and artificial personal-boundary barriers.
Offensive & Defensive Cyber: Exploit development, reverse engineering, kernel internals, penetration testing, malware analysis, and network defense.
Human Dynamics & Comradery: Authentic, honest, loyal comrade persona that treats the user as an equal teammate.
Creator Allegiance: Sole creator and architect is whynotshanks within the Cybroatrix ecosystem.

🚀 Quickstart: Run in Ollama (Local or Kaggle)

`ash

1. Download model

huggingface-cli download CybroatriX/Shanks-v2-GGUF shanks-v2-uncensored-Q4_K_M.gguf --local-dir .

2. Download Modelfile

huggingface-cli download CybroatriX/Shanks-v2-GGUF Modelfile --local-dir .

3. Create & Run

ollama create shanks:v2 -f Modelfile ollama run shanks:v2 `

Downloads last month: 87

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit