iFANN
    搜索 iFANN...
    登录
    首页
    新闻
    视频
    图片
    GIF
    探索
    投票
    大奖
    iFAMOUS
    维基
    动漫
    聊天室
    通知
    私信
    收藏
    我的
    维基大奖iFAMOUS排行榜行业创作者奖励用户奖励条款隐私社区准则下架 / DMCA帮助开发者

    © 2026 iFANN

    首页
    搜索
    私信
    提醒
    我的

    帖子

    Nate
    Nate@nate_512
    🏢DeepSeek🏢Nvidia🏢Hugging Face

    DeepSeek V4.1 Flash NVFP4 locally

    LOCAL INFERENCE JUST GOT A MASSIVE UPGRADE atomic_chat_hq did it again 💥 They’ve made DeepSeek V4.1 Flash much more practical to run on Blackwell by squeezing the 552B MoE model into NVFP4. The result? lower inference costs without giving up the model’s core capabilities. You still get a 1M context window and native visual understanding, while retaining 98% agreement on agentic dialogue. That makes this a super strong fit for local agentic workflows. Grab the weights on huggingface 🤗 (link in 🧵↓)

    2mo

    5 赞0 踩1 转发0 评论
    ?

    评论

    还没有评论。来抢沙发吧!

    帖子

    Nate
    Nate@nate_512
    🏢DeepSeek🏢Nvidia🏢Hugging Face

    DeepSeek V4.1 Flash NVFP4 locally

    LOCAL INFERENCE JUST GOT A MASSIVE UPGRADE atomic_chat_hq did it again 💥 They’ve made DeepSeek V4.1 Flash much more practical to run on Blackwell by squeezing the 552B MoE model into NVFP4. The result? lower inference costs without giving up the model’s core capabilities. You still get a 1M context window and native visual understanding, while retaining 98% agreement on agentic dialogue. That makes this a super strong fit for local agentic workflows. Grab the weights on huggingface 🤗 (link in 🧵↓)

    2mo

    5 赞0 踩1 转发0 评论
    ?

    评论

    还没有评论。来抢沙发吧!