Self-Hosting Local LLMs on a VPS with Ollama
A practical guide to running open models like Llama 3.3 and Qwen 2.5 on your own VPS with Ollama, including CPU sizing, quantization RAM math, and securing the API.
AI Automation
Self-Hosting n8n for Workflow Automation on a VPS
Run n8n on a VPS with Docker Compose and PostgreSQL: webhook, reverse proxy, persistence, security, and backups done right.
AI Automation
Self-hosting n8n on a VPS: sizing RAM for concurrent workflows
Learn exactly how much RAM n8n needs on a VPS for concurrent workflows. Concrete numbers per tier, real-world tips, and hardware mapping for solo devs to teams.