Ollama packages and runs large language models like Llama, Mistral and Gemma locally on your own machine. It exposes a simple CLI and local API server for fully private, offline inference.
ollama.comOllama
Run open-source LLMs locally with a single command
What it does
Ollama downloads open models and runs them on your own computer, from the command line or through a local API that other programs call. It also sells access to larger models that run in Ollama's cloud.
Who it suits
Developers who want a local model behind a script, an editor plugin or an app. Someone who wants a chat window rather than a terminal will find LM Studio or Jan easier. Downloads exist for macOS, Windows and Linux.
Price
Running models on your own hardware is free: the $0 Pay as you go plan has no subscription and no service fee. Cloud plans: Pro at $20 a month or $200 a year, with $60 of usage credits a month; Max at $100 a month; Team at $500 a month, in early access.
Read on ollama.com on 27 October 2026. Prices change: the official page is the reference.
Other sources
Appears in
Tools to run local LLMs, with LM Studio, Jan and Aider
Ollama alternatives, 2 tools that do the same job
Jan vs Ollama, side by side
AI, 12 tools