llama.cpp

Install command: 
brew install llama.cpp

LLM inference in C/C++

https://github.com/ggerganov/llama.cpp

License: MIT

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		 sequoia ✅
sonoma ✅
ventura ✅
macOS on
Intel		 sonoma ✅
ventura ✅
Linux ARM64 ✅
x86_64 ✅

Current versions:

stable ✅ 5410
head ⚡️ HEAD

Depends on when building from source:

cmake 4.0.2 Cross-platform make

Analytics:

Installs (30 days)
llama.cpp 9,147
llama.cpp --HEAD 61
Installs on Request (30 days)
llama.cpp 8,617
llama.cpp --HEAD 61
Build Errors (30 days)
llama.cpp --HEAD 3
llama.cpp 3
Installs (90 days)
llama.cpp 23,791
llama.cpp --HEAD 151
Installs on Request (90 days)
llama.cpp 23,215
llama.cpp --HEAD 151
Installs (365 days)
llama.cpp 65,959
llama.cpp --HEAD 352
Installs on Request (365 days)
llama.cpp 65,376
llama.cpp --HEAD 352
Fork me on GitHub