DeepSeek-V4.1-Flash lands on Hugging Face: 552B params, 1M-token context

victormustar · x · 2026-09-10

Novita Labs announced support for DeepSeek-V4.1-Flash, now available on Hugging Face. Key specs: 552B backbone parameters, native image and text input, up to a 1M-token context window, and continuously controllable reasoning effort.

Related event: DeepSeek Open-Sources V4.1-Flash With Native Vision(39 posts)→

Original post →

More from Models

Models channel →