DeepSeek releases V4.1 Flash: 552B MoE, 1M context, SGLang day-0 support

BanghuaZ · x · 2026-09-10

DeepSeek officially launched V4.1-Flash, the smallest model in its new architecture family, with native visual understanding, faster inference and higher throughput — weights are open. SGLang and Miles shipped day-0 inference and RL support.

Key specs:

The team promises "very exciting performance upgrades" in the coming days.

Related event: DeepSeek Unveils Open-Source V4.1-Flash MoE Model(28 posts)→

Original post →

More from Models

Models channel →