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

A developer has created TurboFieldfare, an inference engine that enables the running of the 4-bit Gemma 4 26B model on M-series Macs with only 2 GB of RAM. This innovation allows for powerful on-device AI experiences, even with models that typically require much more memory.