OmniLLM is a LAN-hosted offline website that consolidates multiple self-hosted LLMs, allowing users to interact with various AI models without internet access.

Key Features:

·       Multiple LLMs – Supports models like LLaMA 2, Mistral, and Gemma.

·       Offline & LAN-Based – Runs entirely on local hardware, accessible via a web interface.

·       Model Switching – Users can choose between different LLMs for various tasks.

·       Fast & Secure – No cloud dependency, ensuring privacy and low-latency responses.

·       User-Friendly Interface – Simple UI for input, and model management.