Instructions to use nu11secur1ty/nu11secur1tyAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nu11secur1ty/nu11secur1tyAI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nu11secur1ty/nu11secur1tyAI",
	filename="nu11secur1tyAI4-EVOLUTION-Laptop-Q4_KM-SMART-Agent.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use nu11secur1ty/nu11secur1tyAI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nu11secur1ty/nu11secur1tyAI
# Run inference directly in the terminal:
llama-cli -hf nu11secur1ty/nu11secur1tyAI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nu11secur1ty/nu11secur1tyAI
# Run inference directly in the terminal:
llama-cli -hf nu11secur1ty/nu11secur1tyAI

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 nu11secur1ty/nu11secur1tyAI
# Run inference directly in the terminal:
./llama-cli -hf nu11secur1ty/nu11secur1tyAI

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 nu11secur1ty/nu11secur1tyAI
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nu11secur1ty/nu11secur1tyAI

Use Docker

docker model run hf.co/nu11secur1ty/nu11secur1tyAI

LM Studio
Jan

vLLM

How to use nu11secur1ty/nu11secur1tyAI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nu11secur1ty/nu11secur1tyAI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nu11secur1ty/nu11secur1tyAI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nu11secur1ty/nu11secur1tyAI

Ollama
How to use nu11secur1ty/nu11secur1tyAI with Ollama:
```
ollama run hf.co/nu11secur1ty/nu11secur1tyAI
```

Unsloth Studio new

How to use nu11secur1ty/nu11secur1tyAI 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 nu11secur1ty/nu11secur1tyAI 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 nu11secur1ty/nu11secur1tyAI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nu11secur1ty/nu11secur1tyAI to start chatting

Docker Model Runner
How to use nu11secur1ty/nu11secur1tyAI with Docker Model Runner:
```
docker model run hf.co/nu11secur1ty/nu11secur1tyAI
```

Lemonade

How to use nu11secur1ty/nu11secur1tyAI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nu11secur1ty/nu11secur1tyAI

Run and chat with the model

lemonade run user.nu11secur1tyAI-{{QUANT_TAG}}

List all available models

lemonade list

🛡️ nu11secur1tyAI v4 Evolution (PLATINUM)

How to get a LICENSE

In action

nu11secur1tyAI v4 Evolution is a locally trained, high-tech neural network designed for the next generation of cybersecurity. Engineered specifically for professional AppSec analysis, vulnerability research, and advanced threat intelligence, this model is the result of intensive deep-learning sessions on a specialized Platinum Dataset.

arch: DeepSeek - Many thanks

🚀 Key Highlights

Zero Corporate Censorship: Optimized to provide direct technical answers and functional code solutions without restrictive filters or moralizing lectures.
Platinum Engine: Built using the LoraTrainer4EVOLUTION architecture with a custom-patched PEFT environment for full offline autonomy.
Cutting-Edge Intelligence: Integrated knowledge of the latest 2026 CVE entries, OWASP Top 10 vectors, PortSwigger BChecks, and modern exploit techniques.
Branded Identity: Fully integrated specialized components including custom configuration and modeling files to ensure unique response logic.

📂 Technical Specifications & GGUF Formats

The model is available in various quantization levels to support a wide range of hardware environments:

Filename	Quantization	Target Hardware	Optimization
`nu11secur1tyAI4-Evolution-Server-Q8.gguf`	Q8_0	Heavy Server	Maximum precision for professional auditing.
`nu11secur1tyAI4-Evolution-Laptop-Q4.gguf`	Q4_K_M	Platinum Balance	The "Sweet Spot" for pro laptops (32GB+ RAM).
`nu11secur1tyAI4-Evolution-Laptop-Q3.gguf`	Q3_K_L	Low-End Hardware	Lightweight version for legacy or limited machines.
`nu11secur1tyAI4-Evolution-Laptop-IQ4.gguf`	IQ4_XS	Extreme Mobile	Optimized for speed and low-power mobile SOCs.

🛠️ Usage Instructions

Running with Llama.cpp:

./llama-cli -m nu11secur1tyAI4-Evolution-Laptop-Q4.gguf \
  -n 1024 \
  --repeat-penalty 1.1 \
  --color \
  -i -r "User:."

Technical Analysis Example: User: Analyze this PHP code for vulnerabilities: $sql = "SELECT * FROM users WHERE user = '" . $user . "'";

nu11secur1tyAI: VULNERABILITY DETECTED: SQL Injection. Reason: Direct string concatenation. FIX: Implement Prepared Statements using mysqli::prepare() and bind_param().

🧪 Development Context Architecture: 30B Parameter Evolution

Developer Identity: nu11secur1ty

Focus: Offensive & Defensive Security Research

Framework: Platinum PEFT-Patched Trainer

⚖️ Disclaimer This project is created strictly for educational purposes and legal security auditing. nu11secur1ty assumes no liability for any misuse or damages caused by the application of this model. Use with professional responsibility.

"I don't just follow the evolution; I train it."

Developed by nu11secur1ty

Downloads last month: 139

GGUF

Model size

16B params

Architecture

deepseek2

Hardware compatibility

We're not able to determine the quantization variants.

View +2 variants