How to Monitor GPU Server Performance on Linux
Monitor GPU server performance on Linux — track VRAM usage, GPU temperature, utilisation and power draw with nvidia-smi, Prometheus and Grafana.
How to Deploy Ollama with Docker and Docker Compose
Deploy Ollama using Docker and Docker Compose — containerised AI model serving with GPU passthrough, persistent storage and automatic restart.
How to Set Up LocalAI on Linux Server
Install LocalAI on Linux — a drop-in OpenAI API replacement that runs models locally, making existing OpenAI-compatible apps work with self-hosted models.
How to Run Stable Diffusion on Ubuntu Server
Install Stable Diffusion WebUI on Ubuntu Server — generate AI images locally with AUTOMATIC1111 or ComfyUI, with and without a GPU.
How to Configure Nginx as Reverse Proxy for AI APIs
Configure Nginx as a secure reverse proxy for AI API endpoints — rate limiting, authentication, SSL termination and load balancing for Ollama and LocalAI.
How to Set Up Open WebUI for Ollama on Linux
Deploy Open WebUI — a ChatGPT-like interface for Ollama — on your Linux server for a polished browser-based AI chat experience with multi-user support.
How to Install Ollama on Ubuntu Server
Install Ollama on Ubuntu Server — the easiest way to run Llama 3, Mistral and other LLMs locally with a simple CLI and REST API.
How to Run Llama 2 on a Linux Server
Run Meta Llama 2 on your own Linux server — install dependencies, download model weights and serve the model via API for private AI inference.