llamafile

A Mozilla.ai tool that packages a language model and its runtime into one executable file that runs on most operating systems with no installation.

26.5k stars, 1.7k forks C++ On GitHub since September 2023

Visit website View on GitHub How to run it

What is llamafile?

llamafile combines llama.cpp with Cosmopolitan Libc, so a model and everything needed to run it fit into a single file. You download it, make it executable and run it on most operating systems and CPU architectures, Windows, macOS and Linux among them. It opens a chat interface in the browser and also serves an API. The project also ships whisperfile, the same idea for speech-to-text with whisper.cpp. It started as a Mozilla Builders project and is now maintained by Mozilla.ai.

Good fit if

  • You want to hand someone a model that just runs, without setup.
  • You need local inference on machines where you cannot install software.

Look elsewhere if

  • You manage many models and switch often: Ollama.
  • You want the newest model support first: llama.cpp moves faster.

Before you adopt it

llamafile is Apache-2.0, with no paid parts. Development is slower than llama.cpp itself: about a dozen commits in the last 90 days.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

llamafile health: is it still maintained?

58 of 100, actively developed

  • Activity
    12 commits in the last 90 days, the latest on 8 October 2026.
    13 / 30
  • Contributors
    6 people wrote the 12 commits of the last 90 days; the most active wrote 58% of them.
    11 / 20
  • Releases
    7 releases in the last 12 months; the latest, 0.10.6, on 15 September 2026.
    17 / 20
  • Replies to issues
    Maintainers answered 55% of recent issues, with a median first reply after 5 days.
    12 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

llamafile license: is it open source?

llamafile uses Apache-2.0, an open-source license approved by the OSI.

  1. September 2023First published on GitHub.
  2. TodayApache-2.0.

How to run llamafile yourself

Docker
No Docker files in the repository
Compose file
None in the repository
Setup effort
Not rated: no compose file to judge from
Kubernetes
No Helm chart in the repository
Desktop and mobile
No app builds in GitHub releases
Interface languages
English only

Install instructions: docs.mozilla.ai or the README on GitHub.

Alternatives to llamafile

  • KoboldCppKoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install. 93 health · AGPL-3.0 · 12.1k stars
  • Local Deep Research~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google,… 82 health · MIT · 9.5k stars
  • AnythingLLMStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first… 94 health · MIT · 67.8k stars
  • LeonLeon is your open-source personal assistant. 57 health · MIT · 17.6k stars
  • NextChatZero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini… 27 health · MIT · 88.9k stars

All 36 projects in AI chat & local LLMs

Questions about llamafile

Is llamafile open source?

Yes. llamafile is published under Apache-2.0, an OSI-approved open-source license.

Is llamafile still maintained?

Its health score is 58 of 100 (actively developed). It had 12 commits in the last 90 days, the latest on 8 October 2026, and its latest release came out on 15 September 2026.

How do I run llamafile?

The repository has no Docker files or app builds, so you build it from source. The README on GitHub has the steps.

What are the alternatives to llamafile?

Close alternatives in the AI chat & local LLMs category include KoboldCpp, Local Deep Research, AnythingLLM.