ollama(@ollama)

we are rolling out the updated model to users who are using deepseek-v4.1-flash as well.

7.0内容质量
we are rolling out the updated model to users who are using deepseek-v4.1-flash as well.

TL;DR · AI 摘要

DeepSeek-V4.1-Flash模型升级，性能提升且成本降低，支持零数据保留的美国托管服务。

核心要点

  • DeepSeek-V4.1-Flash模型在任务完成速度和输出长度上实现帕累托改进
  • Ollama提供美国托管服务，支持零数据保留的云API调用
  • 模型优化适配DeepSeek Harness和腾讯CodeBuddy工具链

结构提纲

按章节快速跳转。

  1. §模型更新公告

    Ollama宣布向使用Deepseek-v4.1-flash的用户推送模型更新。

  2. ·性能优化

    新版本实现基准性能提升、任务完成加速和输出缩短的帕累托改进。

  3. ›托管服务

    支持美国部署的零数据保留托管方案，降低单任务成本。

  4. ·工具适配

    优化集成DeepSeek Harness和腾讯CodeBuddy开发环境。

思维导图

用一张图看清主题之间的关系。

查看大纲文本（无障碍 / 无 JS 友好）
  • DeepSeek-V4.1-Flash升级
    • 性能改进
      • 基准性能提升
      • 任务完成加速
      • 输出长度缩短
    • 部署方案
      • 美国托管服务
      • 零数据保留
    • 工具适配
      • DeepSeek Harness
      • 腾讯CodeBuddy

金句 / Highlights

值得收藏与分享的关键句。

#AI模型#DeepSeek#Ollama#云服务
打开原文

ollama on X: "we are rolling out the updated model to users who are using deepseek-v4.1-flash as well." / X

[](https://x.com/)

ollama on X: "we are rolling out the updated model to users who are using deepseek-v4.1-flash as well."

  • ![Image 2: Avatar](https://x.com/ollama) ollama @ollama 10h ✈ DeepSeek-V4.1-Flash-1017 is on Ollama! US-based hosting with zero data retention. It's strong on agentic tasks while being cheaper per task. Try it on Ollama Cloud: ollama run deepseek-v4.1-flash:1017-cloud Claude Code: ollama launch claude --model Show more ![Image 3: @deepseek_ai](https://x.com/deepseek_ai)DeepSeek @deepseek_ai 23h 🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy,Show more Image 4 [](https://x.com/deepseek_ai/status/2111375640717033777/photo/1) Image 5 [](https://x.com/deepseek_ai/status/2111375640717033777/photo/2) 79 60 813 88K
  • ![Image 6: Avatar](https://x.com/ollama) ollama @ollama we are rolling out the updated model to users who are using deepseek-v4.1-flash as well. 10:06 PM · Oct 17, 2026·4,241 Views 3 22
  • ![Image 7: @keith__w](https://x.com/keith__w) Keith W@keith__w 9h Do we need to use a specific model name when using the cloud API? [](https://x.com/compose/post?in_reply_to=2111586871767671237) 1 146
  • ![Image 8: @SRVpress](https://x.com/SRVpress) Jay Brunet@SRVpress 8h Hmm, when does this happen? [](https://x.com/compose/post?in_reply_to=2111598475024474386) 124

See all the replies

Continue to X

Log in or sign up for X

See what’s happening and join the conversation

Continue with phoneContinue with Apple Continue with Google

or

Log in with username or email