Ollama

Get up and running with large language models locally

D
Score: 49/100
Type
Execution
hybrid
Interface
cli

About

Ollama is the easiest way to run large language models locally. It bundles model weights, configuration, and data into a single package, defined by a Modelfile. Supports macOS, Linux, and Windows with automatic GPU detection for NVIDIA and Apple Silicon.

Performance

1000ms
Cold Start
500MB
Base Memory
100ms
Startup Overhead

Last Verified

Date: Jan 18, 2026
Version: 0.5.4
Method: install success

brew install + ollama run llama3.2 verified on macOS

Languages

PythonJavaScriptGo

Details

Isolation
process
Maturity
production
License
MIT

Links