# mozilla-ai/llamafile

Distribute and run LLMs with a single file.

Repository: https://github.com/mozilla-ai/llamafile
Canonical: https://ross.abutalabs.com/products/llamafile
Homepage: https://docs.mozilla.ai/llamafile
Language: C++
License: NOASSERTION
License Family: other
Topics: cross-platform, gguf, llama-cpp, local-ai, local-inference, local-llm, open-source-ai, single-file-executable, speech-to-text
Last push: 2026-08-26T19:53:20+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 77
- inputs: {"age_days": 1088, "days_push": 7, "days_rel": 30, "gap_med": 28, "n_releases_24m": 14}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 25694, forks 1574 (observed 2026-08-28T04:11:38.409036+00:00)

## What it is
llamafile is a Mozilla project that packages llama.cpp (and whisper.cpp for whisperfile) with Cosmopolitan Libc into single-file executables that bundle an LLM and run it locally on most OSes and CPU architectures with no installation. It provides a chat UI, local API server, and speech-to-text transcription/translation in one portable file.

## Use cases
- run a local llm with a single file
- distribute an open-source model as one executable
- chat with an llm offline without installing anything
- transcribe audio to text locally
- serve a local llm api on any os
- run llm inference on a raspberry pi

## When to choose
- you want zero-install, cross-platform local LLM or speech-to-text execution
- you need to distribute a model plus runtime as one portable file
- you want local inference with no data leaving the machine

## When to avoid
- you need the latest llama.cpp features or fine-grained control (use llama.cpp directly)
- you require multi-GPU or large-scale production serving
- you need a Python/JS library API rather than a standalone executable

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, speech-recognition, http-server, cli, chat-interface
- domain: large-language-models, artificial-intelligence, speech-processing, self-hosted, cross-platform
- platform: windows, bsd, cross-platform, cli
- tags: single-file-executable, gguf, llama-cpp, whisper-cpp, cosmopolitan-libc, local-ai, no-installation, whisperfile, linux, macos, web-server, gpu

## Member repositories
- mozilla-ai/llamafile (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.409036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:00.507726+00:00, confidence not recorded.
  - readme: https://github.com/mozilla-ai/llamafile (fetched 2026-08-28T04:11:38.409036+00:00, sha f0e43a054cdd)
  - homepage: https://docs.mozilla.ai/llamafile (fetched 2026-08-29T07:52:42.792040+00:00, sha 6fcc9620ec71)
  - site_page: https://docs.mozilla.ai/llamafile/getting-started/quickstart (fetched 2026-08-29T07:52:42.801487+00:00, sha 19182e91b2f6)
  - site_page: https://docs.mozilla.ai/llamafile/getting-started/pre-built-llamafiles (fetched 2026-08-29T07:52:42.803452+00:00, sha 27240a1bab91)
  - site_page: https://docs.mozilla.ai/llamafile/using-llamafile/source_installation (fetched 2026-08-29T07:52:42.805060+00:00, sha a354b69d5957)
  - site_page: https://docs.mozilla.ai/llamafile/whisperfile/getting-started (fetched 2026-08-29T07:52:42.806677+00:00, sha 21632a5d4ad8)
- Data as of 2026-08-30T08:39:29.467469+00:00.