# Local and on-premise AI

> Language models and agents on your own infrastructure: on-premise LLMs, hardware sizing, inference servers and privacy-preserving architectures.

Canonical URL: https://www.ruebstudio.de/en/guides/local-ai

## Fundamentals

- [Hardware for Local LLMs: Sizing a GPU Server Properly](https://www.ruebstudio.de/en/guides/local-ai/hardware-local-llm-gpu-server-sizing.md): LLM hardware requirements explained: size a GPU server from the use case, using model size, concurrent users and context length.