What is Ollama?

Local AI

Ollama — An open-source tool for running LLMs locally on your machine with a single command. Supports Llama, Mistral, Qwen, and other models. Handles downloading, quantization, and serving automatically.

FAQ

What is Ollama?

A tool that lets you run LLMs locally with one command. It handles model downloading, quantization, and serving automatically.

Ollama vs llama.cpp?

Ollama is easier (one command). llama.cpp gives more control (custom quantization, server options). Ollama uses llama.cpp under the hood.

Can Ollama use GPU?

Yes. It automatically uses Apple Metal on Mac, and NVIDIA CUDA on Linux/Windows.

Related Terms

Learn Ollama in depth

Free hands-on course with code examples and Google Colab notebooks.

Start Course →