Ollama: Local LLM Runtime
Ollama is a runtime for local execution of large language models. Installation and startup are performed with a single command; manual dependency setup and virtual environments are not required. Local machine → Ollama → Model (Llama, Qwen, Mistral...) Advantages: Data never leaves the local machine No internet connection required for inference No subscriptions or limits Works on CPU (with limited performance) Installation NixOS # configuration.nix services.ollama = { enable = true; # Optional: list of models for auto-loading # models = [ "qwen2.5:7b" ]; }; Apply: ...