FICHA · AUR

node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp

  • language-binding
  • LIBRARY
  • Dependency only
official+codex · reviewed · Jun 2, 2026 description in en

Description

Local AI models can be run from Node.js projects through bindings to llama.cpp. It is useful for developers building applications that need local inference without sending prompts to a remote API.

Model execution can use significant CPU, GPU, memory, and storage. Review model licenses, data privacy, and hardware requirements before integrating it into an application.

Permissions

Permissions not analysed for this source yet.