Ollama
Ollama is an open-source tool that enables users to run large language models (LLMs) directly on their local machines, rather than relying on cloud-based solutions.
Install
Install Ollama.
brew install ollama
Run
Run as a service.
brew services start ollama
Serve.
ollama serve
Download a model. In this case, llama 3.3.
ollama pull llama3.3
Models directory
- Mac -
~/.ollama/models - Linux -
/usr/share/ollama/.ollama/models
Memory requirements
- 8 GB of RAM to run 7B models
- 16 GB to run 13B models
- 32 GB to run 33B models
Resources
Ollama
Interactive graph
On this page
Install
Run
Memory requirements
Resources