niceTeen84
V2EX  ›  OpenAI

本地运行 llama3.1 405B 需要什么样配置的机器?

  •  
  •   niceTeen84 · Jul 26, 2024 · 3353 views
    This topic created in 838 days ago, the information mentioned may be changed or developed.
    5 replies  •  2024-08-24 12:24:26 +08:00
    xtreme1
    xtreme1
    Jul 26, 2024❤️1
    1
    exo https://github.com/exo-explore/exo + 192G MacStudio x2
    yinmin
    yinmin
    Jul 26, 2024
    2
    together 、fireworks 、openrouter 上都有已部署的 llama3.1 405B ,我用了感觉还不如 qwen2 72B ,根本没法和 gpt-4o 、claude 3.5 sonnet 比拼。
    445141126
    445141126
    Jul 26, 2024
    3
    @yinmin 是用中文吗, llama 中文非常拉跨
    antiblahblah
    antiblahblah
    Aug 2, 2024
    4
    @xtreme1 这个配置跑起来什么速度?多少个 token/秒?
    antiblahblah
    antiblahblah
    Aug 24, 2024
    5
    @xtreme1 为什么要 x2 ?
    About   ·   Help   ·   Advertise   ·   Blog   ·   API   ·   FAQ   ·   Privacy   ·   Solana   ·   4760 Online   Highest 6679   ·     Select Language
    创意工作者们的社区
    World is powered by solitude
    VERSION: 3.9.8.5 · 29ms · UTC 03:27 · PVG 11:27 · LAX 19:27 · JFK 22:27
    ♥ Do have faith in what you're doing.