What it does
Big AI models normally need expensive hardware with lots of memory. AirLLM loads the model one piece at a time, so its makers say a model with 70 billion settings can run on a graphics card with only 4GB of memory.
The trade-off is speed: loading pieces in turn is slower than running the whole model at once. It supports many open models and now also some training.
Who it's for
Developers and hobbyists who want to try large open models on ordinary hardware.
Can I use it without coding?
Developers only. A Python library that needs programming. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Linux
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- 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
- AirLLM 70B inference with single 4GB GPUHacker News · Aug 2026
- AirLLM enables 8GB MacBook run 70B LLMHacker News · Dec 2023