FMA3

Assess

Techniques

An x86 fused multiply-add instruction set extension for efficient numerical computing.

Why it's here

Placed in Assess: 1 article(s) of evidence from 1 source(s), led by open-source activity, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.

Evidence (1)

5Hacker News·7/15/2026open_source
Gemma 4 runs on a 13-year-old Xeon with CPU-only optimizations
A Hacker News post describes running Google's Gemma 4 26B mixture-of-experts model on a repurposed 13-year-old HP server with dual Ivy Bridge Xeons and no GPU. After adjusting the inference code to handle pre-AVX2 CPUs, the model reaches about 5.2 tokens per second on the basement machine.