---
title: README
emoji: 😻
colorFrom: purple
colorTo: yellow
sdk: static
pinned: false
---

![](https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg)


Run Open source LLMs and create OpenAI-compatible API services for the Llama2 series of LLMs locally With LlamaEdge!

## Give it a try

Run a single command in your command line terminal.

```
bash <(curl -sSfL 'https://raw.githubusercontent.com/LlamaEdge/LlamaEdge/main/run-llm.sh') --interactive
```

Follow the on-screen instructions to install the WasmEdge Runtime and download your favorite open-source LLM. Then, choose whether you want to chat with the model via the CLI or via a web UI. 

[See it in action](https://youtu.be/Hqu-PBqkzDk) | [GitHub](https://github.com/LlamaEdge/LlamaEdge) | [Docs](https://www.secondstate.io/articles/run-llm-sh/)

## Why?

[LlamaEdge](https://github.com/second-state/LlamaEdge), powered by Rust and WasmEdge, provides a strong alternative to Python in AI inference.

* Lightweight. The total runtime size is 30MB.
* Fast. Full native speed on GPUs.
* **Portable. Single cross-platform binary on different CPUs, GPUs, and OSes.**
* Secure. Sandboxed and isolated execution on untrusted devices.
* Container-ready. Supported in Docker, containerd, Podman, and Kubernetes.

## Learn more

Please visit the [LlamaEdge](https://github.com/second-state/LlamaEdge) project to learn more.