Ollama downloads and runs open models from its own library, from the command line or a chat app on the Mac. Many other apps and coding agents can talk to its local API. Since March 2026 it has an MLX engine on Apple silicon, in preview.
It needs macOS 14 Sonoma or newer. On Apple M-series chips it uses the CPU and GPU; on Intel Macs it runs on the CPU only. Models can take tens to hundreds of GB of disk space.
Ollama is open source (MIT). Local models are free and stay on your Mac. Ollama also sells cloud models, which run on its servers: pay per token, or Pro at $20 a month and Max at $100 a month.
brew install --cask ollama-appbrew install ollamacurl -fsSL https://ollama.com/install.sh | shOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
Ranked against the run models locally listings, from real public data only. How the score works.
Ollama is a product of Ollama; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.