RunLocalAI
runner
Open source
free
4.4/5

Llamafile

Mozilla's single-binary llama.cpp distribution. Download one file, run on any OS without dependencies.

By Fredoline Eruo·Last verified May 6, 2026·22,000 GitHub stars

Overview

Mozilla's single-binary llama.cpp distribution. Download one file, run on any OS without dependencies.

Pros

  • Zero install — single executable
  • Cross-platform
  • No runtime deps

Cons

  • Behind upstream llama.cpp on bleeding edge

Compatibility

Operating systems
macOS
Linux
Windows
GPU backends
NVIDIA CUDA
Apple Metal
CPU
LicenseOpen source · free

Get Llamafile

GitHub
https://github.com/Mozilla-Ocho/llamafile

Frequently asked

Is Llamafile free?

Yes — Llamafile is free to download and use and open-source under a permissive license.

What operating systems does Llamafile support?

Llamafile supports macOS, Linux, Windows.

Which GPUs work with Llamafile?

Llamafile supports NVIDIA CUDA, Apple Metal, CPU. CPU-only inference is also possible but slow.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.