Instructions to use HFShishir/CyberAgent-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use HFShishir/CyberAgent-3B-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 HFShishir/CyberAgent-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf HFShishir/CyberAgent-3B-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 HFShishir/CyberAgent-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf HFShishir/CyberAgent-3B-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 HFShishir/CyberAgent-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf HFShishir/CyberAgent-3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/HFShishir/CyberAgent-3B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use HFShishir/CyberAgent-3B-GGUF with Ollama:
ollama run hf.co/HFShishir/CyberAgent-3B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use HFShishir/CyberAgent-3B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HFShishir/CyberAgent-3B-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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "HFShishir/CyberAgent-3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use HFShishir/CyberAgent-3B-GGUF with Docker Model Runner:
docker model run hf.co/HFShishir/CyberAgent-3B-GGUF:Q4_K_M
- Lemonade
How to use HFShishir/CyberAgent-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull HFShishir/CyberAgent-3B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.CyberAgent-3B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use HFShishir/CyberAgent-3B-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 HFShishir/CyberAgent-3B-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://127.0.0.1:9931/v1 hermes config set model.default HFShishir/CyberAgent-3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use HFShishir/CyberAgent-3B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf HFShishir/CyberAgent-3B-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://127.0.0.1:9931/v1 \ --custom-model-id "HFShishir/CyberAgent-3B-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"
๐ก๏ธ CyberAgent-3B (Fine-Tuned GGUF)
CyberAgent-3B is an autonomous cybersecurity and penetration testing assistant fine-tuned on multi-turn security auditing, vulnerability assessment, and deterministic tool-calling workflows.
Model Details
- Base Architecture: Qwen2.5-3B-Instruct
- Quantization: Q4_K_M (1.93 GB GGUF)
- Primary Focus: External attack surface recon, OWASP vulnerability discovery, anti-hallucination evidence parsing, and server hardening (Nginx/Cloudflare WAF).
Quick Run with Ollama
# 1. Download the GGUF and Modelfile
# 2. Build the Ollama model:
ollama create cyberagent-3b -f Modelfile
# 3. Run directly:
ollama run cyberagent-3b
- Downloads last month
- 79
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support