What it does
TurboFieldfare runs one specific AI model, Google's Gemma 4 26B-A4B, on Apple Silicon Macs. Normally a model this size needs far more memory.
It keeps only a small core of the model in memory and loads the other parts it needs from the Mac's storage as it goes. Its maker says this lets it run on Macs with just 8 GB of memory.
It includes a Mac app, a command-line tool and an experimental local server. The model download is about 15 GB, plus an optional pack for understanding images.
Who it's for
Mac owners and developers who want to run a large AI model locally on modest hardware.
Can I use it without coding?
With some setup. You build the Mac app from source with Apple's developer tools; it needs the latest macOS. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install Apple's developer tools on an Apple Silicon Mac running macOS 26.
- Build and open the TurboFieldfare Mac app following the README.
- Choose Download Model, then Load Model, type a prompt and press Generate.
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
- Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacHacker News · Jul 2026