# Self-Hosted AI Infrastructure

> Self-hosted AI infrastructure by Lim Chee Kin: local LLMs, embeddings, reranking and speech services on an OrangePi 5 Max with Docker and Coolify.

- Page: https://kin.rag.wtf/projects/self-hosted-ai-infra/
- Kind: Open source
- Technologies: Docker, Coolify, LocalAI, Self-Hosting, AI Infrastructure, Open LLMs, Open WebUI

Pioneered and operationalized a self-hosted AI infrastructure using a dedicated local AI server (Coolify, Docker, OrangePi 5 Max). Successfully runs multiple local LLMs (Llama 3.2, DeepSeek-R1, Qwen3, etc.), embeddings, reranking, and STT/TTS services for complete data privacy and operational control.

A self-hosted AI infrastructure using a dedicated local AI server powered by Coolify, Docker, and OrangePi 5 Max. Successfully runs multiple local LLMs (Llama 3.2, DeepSeek-R1, Qwen3, etc.), embeddings, reranking, and STT/TTS services for complete data privacy and operational control.