llama.cpp

Name: llama.cpp
Author: ggml-org

ggml-org

Free

Get Open in MLX Node

MLX Score4.6

PriceFreeno paid plan

RunsOn your Mac

Developerggml-org

LicenceOpenMIT

CategoryRun locally

MacMacCommand line

llama.cpp runs GGUF models, the most widely published format for local AI. It can download a model straight from Hugging Face, chat in the terminal, or serve a web chat and an OpenAI-compatible API.

Apple silicon is a first-class target, through Metal, Accelerate and ARM NEON. Install it with Homebrew or the official install script. No minimum macOS is stated.

It's free and open source (MIT) and runs entirely on your Mac.

How to Get It

Homebrew

brew install llama.cpp

Terminal

curl -LsSf https://llama.app/install.sh | sh

WebsiteVisit

Official downloads only. MLX never re-hosts an app, and never runs a command for you.

MLX Score

4.6out of 5

Homebrew installs (90 days)ahead of 100%

GitHub starsahead of 78%

GitHub: 133,176 stars, last push 2026-11-02 · read 2026-11-02Homebrew: 80,966 installs in 90 days · read 2026-11-02

Ranked against the run models locally listings, from real public data only. How the score works.

Pairs Well With

LlamaRun locally

LM StudioRun locally

Information

Developer: ggml-org
Category: Run models locally
Price: Free
Your data: Runs on your Mac
Licence: MIT
Mac: Runs on a Mac (no minimum stated)
iPhone and iPad: —
Links: Website · Docs · GitHub
Facts checked: 2026-11-01

Sources

github.com/ggml-org/llama.cpp/blob/master/README.md · install script, Apple silicon first-class (Metal), llama cli/serve, OpenAI-compatible server · checked 2026-11-01github.com/ggml-org/llama.cpp/blob/master/LICENSE · licence MIT · checked 2026-11-01formulae.brew.sh/api/formula/llama.cpp.json · Homebrew formula llama.cpp (homepage llama.app) · checked 2026-11-01Icon from GitHub