# EULLM Platform

A self-hosted LLM inference engine written in Rust that runs GGUF models with an OpenAI- and Ollama-compatible API, part of a wider open-source platform for building and distributing EU-based, verticalized language models.

EULLM Engine is a self-hosted LLM inference engine written in Rust, distributed as a single binary with no Python or Docker dependency. It downloads and runs GGUF models such as Qwen, Mistral, DeepSeek, Phi and Gemma, and exposes an OpenAI-compatible and Ollama-compatible API on port 11434.

An install script detects the operating system and GPU, downloads the matching binary, verifies it against release checksums and installs it without root access; models can then be pulled directly from Hugging Face. The engine is one part of a wider planned platform for creating, distributing and running EU-based, verticalized language models for a given domain, language or brand.

It is licensed under AGPL-3.0-or-later, with a separate commercial license offered by its maintainer, I3K Technologies.

Website: https://www.eullm.eu