RepoPilot

mozilla-ocho / llamafile

Search mozilla-ocho/llamafile

GitHub

Get started

Taken from the repository's own files on 21 Oct 2026. RepoPilot has not run these commands.

Prerequisites

The files RepoPilot read do not name a runtime version or package manager.

Commands

Makefile
TaskRunWhat it runs
checkmake checkruns o/$(MODE)/tests
installmake installwhisperfile/whisperfile.1 \ && whisperfile/whisper-server.1 \ && third_party/zipalign/zipalign.1 && mkdir -p $(PREFIX)/bin && $(INSTALL) o/$(MODE)/llamafile/llamafile $(PREFIX)/bin/llamafile && $(INSTALL) o/$(MODE)/whisperfile/whisperfile $(PREFIX)/bin/whisperfile && $(INSTALL) o/$(MODE)/diffusionfile/diffusionfile $(PREFIX)/bin/diffusionfile && $(INSTALL) o/$(MODE)/agentfile/agentfile $(PREFIX)/bin/agentfile && $(INSTALL) o/$(MODE)/transcribefile/transcribefile $(PREFIX)/bin/transcribefile && $(INSTALL) o/$(MODE)/third_party/zipalign/zipalign $(PREFIX)/bin/zipalign && mkdir -p $(PREFIX)/share/man/man1 && $(INSTALL) -m 0644 whisperfile/whisperfile.1 $(PREFIX)/share/man/man1/whisperfile.1 && $(INSTALL) -m 0644 whisperfile/whisper-server.1 $(PREFIX)/share/man/man1/whisper-server.1 && $(INSTALL) -m 0644 third_party/zipalign/zipalign.1 $(PREFIX)/share/man/man1/zipalign.1

Install and use

README.md

Download and run your first llamafile in minutes:

# Download an example model (Qwen3.5 0.8B)
curl -LO https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile

# Make it executable (macOS/Linux/BSD)
chmod +x Qwen3.5-0.8B-Q8_0.llamafile

# Run it
./Qwen3.5-0.8B-Q8_0.llamafile

We chose this model because that's the smallest one we have built a llamafile for, so most likely to work out-of-the-box for you. If you have powerful hardware and/or GPUs, feel free to choose larger and more expressive models which should provide more accurate responses.

Windows users: Rename the file to add .exe extension before running.

Note - Only executables under 4GB can run on Windows, so any llamafile above 4GB won't work. Download the llamafile binary and run it with any external weights/models(GGUF).

Open README.md

Developing

CONTRIBUTING.md

Prerequisites

You will need:

  • GNU make (called gmake on some systems)
  • sha256sum or a working cc
  • wget or curl
  • unzip
  • Git

Windows contributors can use MSYS2 or WSL. See docs/building_dlls.md for detailed Windows setup instructions.

Quick Start

# 1. Fork the repository on GitHub

# 2. Clone your fork
git clone https://github.com/YOUR_USERNAME/llamafile.git
cd llamafile

# 3. Add upstream remote
git remote add upstream https://github.com/mozilla-ai/llamafile.git

# 4. Set up submodules, patches, and toolchain
make setup

# 5. Build with cosmocc's make
.cosmocc/4.0.2/bin/make -j8

# 6. Run the default test suite
.cosmocc/4.0.2/bin/make check

make setup initializes submodules, applies llamafile-specific patches, and downloads the cosmocc toolchain into .cosmocc/.

For builds and tests, use .cosmocc/4.0.2/bin/make, not your system make.

Open CONTRIBUTING.md