llamafile
Mozilla AIllamafile packages a large language model and the software to run it into a single cross-platform executable that runs without installation on macOS, Linux, BSD, and Windows. It combines llama.cpp with Cosmopolitan Libc to produce one file that works across operating systems and CPU architectures. Originally a Mozilla Builders project, it is now maintained by Mozilla.ai and ships a companion single-file speech-to-text tool, whisperfile.
GitHub's repository classifier reports NOASSERTION for this repo; the LICENSE body and README disagree with it, and the openness score follows the LICENSE body. Verified 2026-08-09 via GitHub, the LICENSE body, and the README.
Openness
5 high confidence- license
- Apache-2.0(OSI)+MIT(OSI, for llama.cpp/whisper.cpp deltas)
- source
- public(mozilla-ai/llamafile)
- core-gated
- ungated
Fully OSI-licensed, source public, single-file llama.cpp+Cosmopolitan distribution; no proprietary tier. GitHub org renamed from Mozilla-Ocho to mozilla-ai; same repo, license and openness posture unchanged. GitHub's own classifier still reports NOASSERTION/"Other" for this repo, which the LICENSE body and README's licensing section both contradict with a plain Apache-2.0 (+ MIT deltas) statement.
- https://github.com/mozilla-ai/llamafile recorded 2026-08-09
repo metadata: "isPrivate":false,"isArchived":false,"visibilityLabel":"Public"; License badge in README reads Apache 2.0; no pricing/paid-tier link anywhere on the repo page or in the documentation links listed
- https://raw.githubusercontent.com/mozilla-ai/llamafile/main/LICENSE recorded 2026-08-09
The Apache 2.0 License / Copyright 2023 Mozilla Foundation / Licensed under the Apache License, Version 2.0
- https://raw.githubusercontent.com/mozilla-ai/llamafile/main/README.md recorded 2026-08-09
While the llamafile project is Apache 2.0-licensed, our changes to llama.cpp and whisper.cpp are licensed under MIT (just like the projects themselves) so as to remain compatible and upstreamable in the future
Adoption
3 low confidenceDistributed as single-file binaries rather than as a package, so there is no download or pull count to band; GitHub stars are the only honest signal, and because a star is not a use they cap the level at 3. The 25,548 stars on the project's single repository fall in the >10K stars band, level 3. A popular local-inference convenience tool, but with no verified usage figure behind it.
- https://github.com/mozilla-ai/llamafile recorded 2026-08-09
"stargazerCount":25523,"watcherCount":225,"forksCount":1544
Capability
3 medium confidenceOptimized for portability and zero-install local inference rather than datacenter throughput. Because it is built on llama.cpp it has none of the continuous-batching or tensor-parallel server scaling that vLLM offers, which places it mid-tier on an axis whose frontier is the high-throughput serving engines.
- https://raw.githubusercontent.com/mozilla-ai/llamafile/main/README.md recorded 2026-08-09
combining llama.cpp with Cosmopolitan Libc into one framework...single-file executable...runs locally on most operating systems and CPU architectures, with no installation; llamafile also includes whisperfile
- https://raw.githubusercontent.com/mozilla-ai/llamafile/main/README_0.10.0.md recorded 2026-08-09
added Metal support: GPU on MacOS ARM64...Brought back cuda support on Linux...added TUI support: you can now directly chat with the chosen LLM from the terminal, or run the llama.cpp server using the --server parameter...What's missing: GPU support for Windows (and for whisperfile)
Verified 2026-08-09