Atome-FE/llama-node
A Node.js library for running large language model inference locally on CPU using Rust-based backends.
Not currently ranked — collecting fresh signals.
star history
llama-node provides a Node.js binding for running LLM inference using llama-rs, llama.cpp, and rwkv.cpp as backends. It supports models including llama, alpaca, gpt4all, vicuna, and rwkv, running entirely locally on laptop CPU without cloud dependencies. The project is built with N-API and Rust (NAPI-RS) for performance.
Frequently asked
- What is Atome-FE/llama-node?
- A Node.js library for running large language model inference locally on CPU using Rust-based backends.
- Is llama-node open source?
- Yes — Atome-FE/llama-node is open source, released under the Apache-2.0 license.
- What language is llama-node written in?
- Atome-FE/llama-node is primarily written in Rust.
- How popular is llama-node?
- Atome-FE/llama-node has 861 stars on GitHub.
- Where can I find llama-node?
- Atome-FE/llama-node is on GitHub at https://github.com/Atome-FE/llama-node.