Run private models on your own machine with Ollama.
Your laptop. Your AI.
Run open models privately on your own laptop or server, and plug them into your apps and tools.
Local & Open Models.
Install Ollama, pick a model that fits your RAM, chat in the terminal and call it from your own code.
Install, choose a model for your hardware and connect a chat interface.
A rough rule for local models: a 4-bit 7–8B model needs about 5–6GB of memory. Start small, then step up if it's too weak.
Ollama unloads idle models after a few minutes. Set keep_alive on requests if you want instant replies during a session.