17:03
2026-07-15
sourcefeed.dev
artificial-intelligence
Old Xeons Can Run Gemma 4 at Reading Speed
A 26-billion-parameter Gemma 4 mixture-of-experts model can run at reading speed on decade-old Xeon CPUs, achieving ~5.2 tokens per second on a dual-socket 2013 Ivy Bridge system with no GPU, thanks t…