# DeepSeek-V4.1-Flash 上架 Hugging Face：552B 参数 MoE 模型，新架构家族最小款

- 来源：🚨 AI News | TestingCatalog (@testingcatalog)
- 发布时间：2026-09-10 14:13
- AIHOT 分数：75
- AIHOT 链接：https://aihot.news/items/cmtv5d20m037qro3q96umujxp
- 原文链接：https://x.com/testingcatalog/status/2097931430663717139

## AI 摘要

DeepSeek 发布 DeepSeek-V4.1-Flash 并上架 Hugging Face，为 552B 参数 MoE 模型，采用新的 Encoder-Decoder 结构、新预训练方法和更大规模强化学习后训练。

## 正文

DeepSeek V4.1 Flash is now available on Huggingface!

552B parameters MoE model with a new Encoder-Decoder structure.

V4.1 Flash adopted a new pre-training method and underwent larger-scale reinforcement learning post-training.

The smallest model in DeepSeek new architecture family, with native visual understanding.

### 引用推文

> DeepSeek：🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual unders...