← back to the directory
Application Inference & Serving

Ollama

1Run 2open 3models 4on 5your 6machine.

the six Ws · specification

W1 Who

Open-source local model runtime.

W2 What

Pull and serve open LLMs with one command.

W3 Where

Runs on your laptop or server, offline.

W4 When

When you want local, private inference.

W5 Why

Removes the cloud from running open models.

W6 With

A machine with enough RAM or GPU.

GoLocalModels

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.