Skip to content

install.md

Latest commit

 

History

History
78 lines (53 loc) · 1.79 KB

install.md

File metadata and controls

78 lines (53 loc) · 1.79 KB

Install pre-built version of llama.cpp

Install via Windows Mac Linux
conda-forge ✅ ✅ ✅
Winget ✅
Homebrew ✅ ✅
MacPorts ✅
Nix ✅ ✅

conda-forge (Windows, Mac and Linux)

conda-forge provides builds for:

  • CUDA (Windows and Linux)
  • Vulkan (Windows and Linux)
  • Apple Metal (macOS)
conda install -c conda-forge llama-cpp
mamba install -c conda-forge llama-cpp
# Project-local installation
pixi add llama-cpp

# Global installation
pixi global install llama-cpp

This distribution is managed on conda-forge/llama-cpp-feedstock.

Shall you have any problems, please open an issue on its issue tracker.

Winget (Windows)

winget install llama.cpp

The package is automatically updated with new llama.cpp releases. More info: ggml-org#8188

Homebrew (Mac and Linux)

brew install llama.cpp

The formula is automatically updated with new llama.cpp releases. More info: ggml-org#7668

MacPorts (Mac)

sudo port install llama.cpp

See also: https://ports.macports.org/port/llama.cpp/details/

Nix (Mac and Linux)

nix profile install nixpkgs#llama-cpp

For flake enabled installs.

Or

nix-env --file '<nixpkgs>' --install --attr llama-cpp

For non-flake enabled installs.

This expression is automatically updated within the nixpkgs repo.