About Ollama
Ollama is an open-source app for downloading and running open AI models on your own hardware. It runs on macOS, Windows and Linux and suits developers and privacy-minded users who want a local alternative to hosted chatbots, with an optional cloud service when a model is too large to run locally.
Key benefits of Ollama include:
- Local and unlimited: Running models on your own hardware is free and has no usage caps.
- Privacy: Ollama says prompts are never stored or trained on, and local models keep data on your machine.
- Wide model selection: Cloud models include options such as gpt-oss, DeepSeek, Kimi, GLM, Gemma and Mistral Large, priced per million tokens.
- Tool calling: Cloud models trained for tools are tested for tool calling and agent workflows before release.
- Flexible cloud billing: Pay as you go per token with no subscription, or choose Pro ($20/month) or Max ($100/month) plans that include usage credits.
For someone leaving ChatGPT, Ollama gives control over which model runs and where your data goes, and local use costs nothing beyond your hardware. The trade-off is that local performance depends on your machine, and the largest models need either powerful hardware or Ollama's paid cloud. It is primarily a model runner rather than a polished chat product, so expect some setup and possibly a separate interface for a ChatGPT-like experience.

