#Avx2

A storage appliance that shipped before AVX2 existed now runs Google's Gemma 4 26B in my basement, no GPU. Here's how we got a modern MoE model onto a CPU older than the instructions its inference engine assumed were there.

Notes from getting F5-TTS, StyleTTS2, kokoro, and whisper.cpp to run on a 2010-era AMD Phenom II X6.