4 guides
Build a fully self-hosted AI coding agent on Windows with Cline and a local model via Ollama or LM Studio. Private, no API cost, in VS Code — setup and trade-offs.
Run GLM-4.5-Air locally on WSL with Ollama and connect it to a coding agent. Install, model pull, OpenAI-compatible endpoint, hardware needs, and the fixes.
Run Qwen3-Coder locally with LM Studio on Windows and connect it to OpenCode. Model download, the local server, config, hardware needs, and the common fixes.
Run a DeepSeek model locally with Ollama on Windows and connect it to Claude Code via Claude Code Router. Install, model pull, config, hardware needs, and fixes.