Running models locally keeps inference on your machine: nothing uploaded, works offline, no quota to exhaust. Here are the runtimes, the interfaces and assorted assistants.
A tool for running open-source large language models on your own machine. One command pulls and starts supported models such as Llama, Qwen and Gemma, with all inference happening locally so data never leaves the computer. It ships a command-line interface and a REST API for wiring models into your own scripts and apps, which suits offline use and privacy-sensitive work.
A keyboard-driven launcher and productivity tool for macOS. A shortcut opens a search box where you can launch apps, find files, run calculations, manage the clipboard, control windows and reach third-party services through extensions. It gathers everyday actions behind one entry point, which suits people who prefer to stay on the keyboard instead of switching to the mouse.