15:34
2026-07-15
neomindlabs.com
artificial-intelligence
Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon with no GPU
A developer running Google's Gemma 4 26B mixture-of-experts model on a 13-year-old HP StoreVirtual server with dual Ivy Bridge Xeons and no GPU achieved 5 tokens per second by patching inference kerne…