FICHA · AUR

llama.cpp

Port of Facebook's LLaMA model in C/C++

  • llm-inference-tool
  • CLI
  • Dev
  • Launchable
  • Runs in terminal
official+codex · reviewed · Jun 2, 2026 description in en

Description

Local LLM inference can run on a machine without relying on a hosted chat service.

This package is useful for developers and advanced users who want llama.cpp tools for running compatible language models. It provides inference software; model files must be obtained separately.

Local AI still processes sensitive prompts and can use large CPU, memory, disk, or GPU resources. Review model sources and do not expose servers unintentionally.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.