llama.cpp

Install command: 
brew install llama.cpp

LLM inference in C/C++

https://llama.app

License: MIT

Development: Pull requests

Formula JSON API: /api/formula/llama.cpp.json

Formula code: llama.cpp.rb on GitHub

Bottle (binary package) installation support provided for:

macOS on
Apple Silicon		 tahoe ✅
sequoia ✅
sonoma ✅
macOS on
Intel		 sonoma ✅
Linux ARM64 ✅
x86_64 ✅

Current versions:

stable ✅ 9960
head ⚡️ HEAD

Depends on:

ggml 0.16.0 Tensor library for machine learning
openssl@3 3.6.3 Cryptography and SSL/TLS Toolkit

Depends on when building from source:

cmake 4.4.0 Cross-platform make

Analytics:

Installs (30 days)
llama.cpp 41,396
llama.cpp --HEAD 340
Installs on Request (30 days)
llama.cpp 41,125
llama.cpp --HEAD 339
Build Errors (30 days)
llama.cpp --HEAD 38
llama.cpp 38
Installs (90 days)
llama.cpp 109,247
llama.cpp --HEAD 1,274
Installs on Request (90 days)
llama.cpp 108,162
llama.cpp --HEAD 1,273
Installs (365 days)
llama.cpp 281,304
llama.cpp --HEAD 2,568
Installs on Request (365 days)
llama.cpp 246,481
llama.cpp --HEAD 2,567