Active params in L2 cache hit 14,572 tok/s on Intel Emerald Rapids with AMX

GregoryDiamos · x · 2026-09-07

Gregory Diamos needed a 10k tok/s CPU model for data processing, so he gave Claude Code a pile of tokens to build an outrageously small neural net. With active params fitted into L2 cache on an Intel Emerald Rapids CPU with AMX, it reaches 14,572 tok/s. He shares three interesting discoveries and argues tiny nets deserve a revisit for inference/data-processing workloads.

Related event: Developer Uses Claude Code to Build Tiny CPU Model Hitting 10k+ tok/s(4 posts)→

Original post →

More from Infra

Infra channel →