Command-line tool

llama.cpp

brew/llama.cpp

Checked 25 Oct 2026, 21:09 UTC · Listing refreshed from Homebrew, winget, npm, Scoop and cargo; npm packages checked against OSV.dev

LLM inference in C/C++ llama ggml

Website Source

At a glance

Type

Command-line tool

Install on

Windows, macOS, Linux

Last checked

25 Oct 2026, 21:09 UTC

Install it

Windows

winget install --id ggml.llamacpp -e

macOS

brew install llama.cpp

Linux

brew install llama.cpp

Start up LLM [m]odel and interface

llama-cli -m path/to/model

Start with setup prompt [c]ontext size

llama-cli -m path/to/model -c number

Start with set offload [n]umber of layer [g]pu [l]ayers

llama-cli -m path/to/model -ngl auto

Browse

• Calling other AI models

Related command-line tools

• koboldcpp
  A simple one-file way to run various GGML models like LLAMA, ALPACA, VICUNA
• llama-swap
  Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc.
• LlamaForge Manager
  LlamaForge Manager (Windows package; no description in the winget index)
• lmstudio
  Discover, download, and run local LLMs (llama.cpp, MLX). Chat UI and OpenAI-compatible local API server.
• whisper.cpp
  Port of OpenAI's Whisper model in C/C++
• lmstudio-bionic
  Local-first AI agent for work and code. Runs open models on your machine (llama.cpp) or in LM Studio Cloud, with…
• openvino
  Open Visual Inference And Optimization toolkit for AI inference
• text-embeddings-inference
  Blazing fast inference solution for text embeddings models

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents