← back to the directory
Application Inference & Serving

llamafile

1Run 2LLMs 3from 4a 5single 6file

the six Ws · specification

W1 Who

Maintained by Mozilla (Ocho) and Justine Tunney.

W2 What

Packages an LLM and runtime into one executable file.

W3 Where

Runs locally as a single cross-platform binary.

W4 When

When you want zero-setup local model distribution.

W5 Why

One file runs anywhere without installing dependencies.

W6 With

A machine; the model is bundled in the file.

W7 Watch

Vendor-maintained (Mozilla); open-source (Apache-2.0). Runs fully local, so data stays on your machine and works offline.

LocalInferencePortable

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.