---
id: 20260913-T0-01
title: "DeepSeek v4.1-Flash发布：763B参数、因果编码器-解码器架构、带视觉能力"
title_en: "DeepSeek v4.1-Flash: 763B Parameters, Causal Encoder-Decoder, Vision Capabilities"
url: https://ai.daily.yangsir.net/daily/20260913-T0-01
issue_date: 2026-09-13
publish_date: 2026-09-12T05:56:05.000Z
category: release
source_name: "Latent Space"
source_url: https://www.latent.space/p/ainews-deepseek-v41-flash-763b-p8b
---

# DeepSeek v4.1-Flash发布：763B参数、因果编码器-解码器架构、带视觉能力

DeepSeek发布v4.1-Flash，采用763B参数、P8B-D16B的因果编码器-解码器架构，并首次加入视觉能力。Latent Space评价称，从规格来看这更像是v5级别的大版本，而非小版本迭代。该模型在参数规模和架构设计上都有明显变化，视觉能力的加入也扩展了应用场景。对关注开源大模型进展的开发者来说，这是DeepSeek在架构路线上的一个重要节点。

## English Version

**DeepSeek v4.1-Flash: 763B Parameters, Causal Encoder-Decoder, Vision Capabilities**

DeepSeek released v4.1-Flash, featuring a 763B-parameter causal encoder-decoder architecture with P8B-D16B and vision capabilities for the first time. Latent Space noted that by specifications, this feels more like a v5-level major release than a minor iteration. The model shows significant changes in parameter scale and architecture design, and the addition of vision expands its use cases. For developers tracking open-source LLM progress, this marks an important architectural milestone for DeepSeek.

---

**来源**：[Latent Space](https://www.latent.space/p/ainews-deepseek-v41-flash-763b-p8b)

**详情页**：https://ai.daily.yangsir.net/daily/20260913-T0-01

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*