O
Ollama
Tool for running large language models locally on Mac and Linux.
Visit website
👁 3227 views
About Ollama
Ollama simplifies running open-source LLMs locally -- download any model from LLaMA, Mistral, Gemma, or Phi with one command. Starts a local API server compatible with OpenAI format for easy integration. 70,000 GitHub stars. M1/M2/M3 Mac optimized with Apple Neural Engine support.
AI summary
Ollama runs LLaMA, Mistral, and Gemma locally with a one-command download and OpenAI-compatible API.