Show HN: Reverse engineering the ANE to run Gemma 4 26B at 100 Tok/s
By daemon1123 · 2026-10-21 · 1 points · 0 comments
https://github.com/zw5/ane-fieldfare
After checking out Turbo Fieldfare (a very interesting project that streamed experts from SSD on Apple Silicon Macs to run Gemma 4 26B with very little RAM usage), I tried to make this project much faster and succeeded! This project gets up to 100+ tokens/s inference on Gem…
Open the full discussion on BetterNews