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

TurboFieldfare is an open-source engine that enables running Google's Gemma 4 26B language model on Apple Silicon Macs with just 2 GB of RAM by streaming model experts from SSD storage instead of loading the entire 14.3 GB model into memory. Built entirely in Swift and Metal, it achieves this by keeping only the 1.35 GB shared core and KV cache in RAM while dynamically loading the specific experts needed for each token. The project demonstrates practical AI inference optimization, with benchmarks showing 5-6 tokens/second on an 8 GB M2 MacBook Air and 31-35 tokens/second on an M5 Pro.