LLM tutorials
Step-by-step LLM tutorials: run Ollama models on a CPU server, connect them to OpenCode, and route API and local models through a self-hosted LiteLLM gateway.
4 tutorials
- 11 min read
How to Install OpenCode on Ubuntu 24.04 with API or Ollama Models
Install OpenCode 2 on Ubuntu 24.04 in 8 steps: run it as a separate user, connect an API key or a local Ollama model, use tmux, and limit shell access.
Read tutorial - 11 min read
How to Install Ollama on Ubuntu 24.04 with Open WebUI (CPU Only)
Install Ollama on Ubuntu 24.04 without a GPU, keep its API on 127.0.0.1:11434, and run Open WebUI in Docker behind Nginx, HTTPS and UFW in 8 steps.
Read tutorial - 18 min read
How to Set Up Claude Code with Ollama on an Ubuntu 26.04 Server
Set up Claude Code with open models from Ollama on an Ubuntu 26.04 server with no GPU: local models that keep code on your server, or cloud models for speed.
Read tutorial - 15 min read
How to Self-Host LiteLLM Proxy with Docker Compose on Ubuntu 24.04
Self-host LiteLLM proxy on Ubuntu 24.04 with Docker Compose and PostgreSQL in 9 steps: a virtual key per app, fallbacks, HTTPS, and Codex and Claude Code.
Read tutorial