Home Projects turbo-fieldfare
turbo-fieldfare

turbo-fieldfare

by drumih · GitHub

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

View on GitHub
In plain words

Run a large AI model on your Mac with limited memory, making it accessible even for devices with less RAM.

⭐ Stars
🍴 Forks
🔥 Trending
📜 License
Commercial use OK
📅 Created
🔄 Last commit
🏷️ Category
💻 Language
🖥️ Self-hostable
Likely
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
turbo-fieldfare — GitHub preview card
📈 Star history
3k2k
2026-07-312026-08-01
📈 Track turbo-fieldfare

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

turbo-fieldfare has 2.9k stars on GitHub. It has been forked 123 times. turbo-fieldfare is written mainly in Swift. It has been in active development since 2026. turbo-fieldfare is available under the Apache-2.0 license. Its main topics are apple-silicon, gemma, gemma4, gemma4-26b-a4b.

Frequently asked questions

What is turbo-fieldfare?

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Is turbo-fieldfare open source?

turbo-fieldfare is an open-source project. It is released under the Apache-2.0 license.

Is turbo-fieldfare free?

Yes. turbo-fieldfare is free and open source — you can use, modify and self-host it.

What license does turbo-fieldfare use?

turbo-fieldfare is available under the Apache-2.0 license.

What language is turbo-fieldfare written in?

turbo-fieldfare is written mainly in Swift.

🏅 Maintainer of this project?
olud.ai badge — turbo-fieldfare

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=drumih-turbo-fieldfare)](https://olud.ai/project/drumih-turbo-fieldfare.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.