DeepSeek unveils V4.1-Flash: smallest model in new architecture family with native vision

zephyr_z9 · x · 2026-09-10

DeepSeek officially introduced V4.1-Flash, the smallest model in its new architecture family, with native visual understanding, designed for greater capability, faster inference and higher throughput as a stepping stone to larger models. Retweeter Dorialexander quipped "model is data." The model offers 552B backbone params (16B active), 1M context, and day-0 support in SGLang.

Related event: DeepSeek Releases V4.1 Flash: New Architecture, Native Vision, MIT Open Weights(35 posts)→

Original post →

More from Models

Models channel →