Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Keyword: Prompt-library

Publisher: Github.com

Published: Jul 29, 2026

Gemma 4 26B-A4B inference in about 2 GB of RAMA custom Swift + Metal runtime for any Apple Silicon Mac, even the 8 GB ones. Quick start · Local server · Benchmarks · Contribute results · How… [+12893 chars]

Read Full Story ↗