GilGamez-com/Leviathan-v4.2-GGUF

🐉 Leviathan v4.2 (GGUF & Edge Deployment)

This repository hosts official GGUF quantizations and edge deployment assets for Leviathan v4.2, the enterprise vision-language model and autonomous orchestrator developed by GilGamez.

For model architecture, capabilities, and the full base LoRA weights, visit the primary model card:
👉 GilGamez-com/Leviathan-v4.2

---

⚡ Deployment Options

1. Ollama (Recommended)

Leviathan v4.2 includes a pre-configured Modelfile in this repository optimized for Ollama:

# Clone or download the Modelfile and GGUF
ollama create leviathan-v4.2 -f Modelfile

# Start an interactive session
ollama run leviathan-v4.2

---

2. llama.cpp CLI & Server

Run high-performance, low-latency CPU/GPU offloaded inference using llama.cpp:

# Interactive CLI
./llama-cli -m Leviathan-v4.2.Q4_K_M.gguf -p "You are Leviathan v4.2, an autonomous AI assistant." -cnv

# Local OpenAI-compatible API Server
./llama-server -m Leviathan-v4.2.Q4_K_M.gguf --port 8080 -ngl 33 --ctx-size 4096

---

🛡️ Organization & Contact

• Organization: GilGamez
• Website: https://www.gilgamez.com
• Main Model: GilGamez-com/Leviathan-v4.2