Instructions to use arcanicai/Con0-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 arcanicai/Con0-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 arcanicai/Con0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf arcanicai/Con0-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 arcanicai/Con0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf arcanicai/Con0-GGUF: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 arcanicai/Con0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf arcanicai/Con0-GGUF: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 arcanicai/Con0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arcanicai/Con0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/arcanicai/Con0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use arcanicai/Con0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcanicai/Con0-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": "arcanicai/Con0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/arcanicai/Con0-GGUF:Q4_K_M

Ollama
How to use arcanicai/Con0-GGUF with Ollama:
```
ollama run hf.co/arcanicai/Con0-GGUF:Q4_K_M
```

Unsloth Studio

How to use arcanicai/Con0-GGUF 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 arcanicai/Con0-GGUF 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 arcanicai/Con0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arcanicai/Con0-GGUF to start chatting

How to use arcanicai/Con0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arcanicai/Con0-GGUF:Q4_K_M

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": "arcanicai/Con0-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use arcanicai/Con0-GGUF with Docker Model Runner:
```
docker model run hf.co/arcanicai/Con0-GGUF:Q4_K_M
```

Lemonade

How to use arcanicai/Con0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arcanicai/Con0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Con0-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use arcanicai/Con0-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 arcanicai/Con0-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 arcanicai/Con0-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use arcanicai/Con0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arcanicai/Con0-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 "arcanicai/Con0-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"

Con0 (GGUF)

GGUF quantizations of Con0 - a state-of-the-art vision-language model specialized for cyber security, developed by Arcanic AI in collaboration with NextZero.

Full model (BF16): arcanicai/Con0

Con0 is built to think like a security auditor. It reads code, logs, screenshots, and infrastructure diagrams, and surfaces vulnerabilities - from classic web-application flaws to the newest AI-agent attack surfaces - with actionable remediation guidance.

What Con0 audits

Web & application security

SQL injection (SQLi) - time-based, boolean-based, error-based, and blind variants across query builders and ORMs
Cross-site scripting (XSS) - reflected, stored, and DOM-based injection
Cross-site request forgery (CSRF), server-side request forgery (SSRF)
Command injection, path traversal, XXE, deserialization
Broken authentication, broken access control, and IDOR
OWASP Top 10 coverage, code review, and secure-configuration assessment

AI & agent security

Prompt injection and jailbreak surface analysis
Tool-calling and function-dispatch misuse
Least-privilege / permission-scope review
Multi-step agent threat modeling

General security

Vulnerability triage and CVE context mapping
Incident analysis from logs, traces, and screenshots
Secure-code guidance and remediation planning

Available quantizations

File	Size	Notes
`Con0-Q3_K_M.gguf`	~13 GB	Smallest, lowest quality - best for low-VRAM setups
`Con0-IQ4_XS.gguf`	~15 GB	4-bit non-linear, very efficient
`Con0-Q4_K_S.gguf`	~16 GB	4-bit small
`Con0-Q4_K_M.gguf`	~16 GB	4-bit medium - recommended balance
`Con0-Q5_K_M.gguf`	~19 GB	5-bit, higher quality
`Con0-Q8_0.gguf`	~28 GB	8-bit, near-lossless
`mmproj-Con0-F16.gguf`	928 MB	Vision projector (load alongside for image/video)

Quick start (llama.cpp)

Requires a recent llama.cpp build with qwen35 support (LM Studio ≥ 0.4.6 or llama.cpp runtime ≥ b10488).

# Text-only
./llama-cli -m Con0-Q4_K_M.gguf -p "Review this code for SQL injection vulnerabilities."

# With vision (load the projector for image inputs)
./llama-cli -m Con0-Q4_K_M.gguf   --mmproj mmproj-Con0-F16.gguf   --image path/to/screenshot.png   -p "Analyze this screenshot for security issues."

Memory requirements

Quantization	Approx. RAM/VRAM
Q3_K_M	~16 GB
IQ4_XS / Q4_K_S / Q4_K_M	~19 GB
Q5_K_M	~22 GB
Q8_0	~31 GB

Benchmarks

Benchmark evaluation is in progress and will be published here (see the main arcanicai/Con0 card).

About the developers

Con0 is developed by Arcanic AI, a research lab focused on reliable and secure AI systems, in partnership with NextZero.

License

Apache 2.0.

Downloads last month: 1,445

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

16-bit

Model tree for arcanicai/Con0-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

arcanicai/Con0

Quantized

(1)

this model