Plain-AyI
← All projects
AI models & research

RWKV

An open AI language model design that aims to match transformer models while using less memory and computing power.

Research-backed

What it does

RWKV is a different way to build AI language models. Most chat AIs use "transformers", which slow down and need more memory as a conversation gets longer. RWKV works more like an older design called an RNN, and its makers say it keeps a constant speed and memory use however long the text gets.

Its makers say it still trains as efficiently as a transformer and performs well on language tasks. The latest version is called RWKV-7 "Goose".

Model weights, chat apps and tools for running it on phones and desktops are linked from the README. It's a Linux Foundation AI project.

Who it's for

AI researchers and engineers interested in efficient model designs, and hobbyists who want to try a different kind of model.

Can I use it without coding?

Developers only. Training and running the code needs programming and a graphics card. Separate chat apps are linked for trying it. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Computer
Works best on a powerful computer or one with a graphics card (GPU)
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it