Skip to content
BYOK Tools

llamafile

Run an LLM from a single executable file on any OS.

4.0 editor score•Local AI•Free & open source

Overview

llamafile, a Mozilla project, packages model weights and llama.cpp into one portable executable that runs on macOS, Windows and Linux. It launches a local chat UI and OpenAI-compatible server.

  • Single-file distribution
  • Built-in web UI
  • OpenAI-compatible server
  • CPU and GPU support

Our verdict

What we like

  • Zero install
  • Portable across OSes

Watch out for

  • Large file sizes

Works with these providers

Keys from these providers work in this app. Usage is billed by the provider at its list price.

BYOK Key Safety Score

Key handling in llamafile

How we score
85/ 100

Grade A

Your key is stored on your device and requests go directly to the provider.

  • Key storage

    Key stays on your device; requests go direct to the provider.

    40/40
  • Auditable code

    Open source: anyone can verify how keys are handled.

    25/25
  • Self-hosting

    Runs as a local app, but not as a self-hosted service.

    8/15
  • Offline option

    Supports local models, so no key is needed at all for private work.

    10/10
  • Provider choice

    1 provider option, which lets you pick the provider whose data terms you trust.

    2/10

Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.

llamafile FAQ

Does llamafile support bring your own key?
Yes. llamafile accepts your own API key from OpenAI-compatible. Usage is billed by the provider at its API rates.
Where does llamafile store my API key?
On your device. Requests go directly from llamafile to the provider. Its BYOK Tools Key Safety Score is 85/100.
Is llamafile free?
Open source: Free & open source. API usage is billed separately by your model provider.
Is llamafile open source?
Yes. The source code is at https://github.com/Mozilla-Ocho/llamafile.
Can llamafile run local models?
Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
Which platforms does llamafile support?
macOS, Windows, Linux, CLI.

Community reviews

No reviews yet.