I think flash usually means MoE, not dense

PcChip • today at 6:05 PM • 2 replies • view on HN

jephs • today at 6:15 PM

Every frontier model is MoE these days! Flash or otherwise. Sparsity just gets you more bang for your buck.

terhechte • today at 6:08 PM

Not really. “Flash” generally means fast or cost-efficient, not specifically MoE (Mixture of Experts).

- DeepSeek V4 Flash: 284B / 13B active MoE

- DeepSeek V4 Pro: 1.6T / 49B active MoE

- DeepSeek V4.1 Flash: 552B / 8B input, 16B output MoE

alt Hacker News