Apple 展示用 MLX 在 Mac Studio 集群运行近万亿参数模型

Apple ML Research: Muse Spark Open with MLX on Mac Studio

AI 导读

Apple ML Research 演示如何用最新版 MLX 在 Mac Studio 上运行近万亿参数的前沿模型 Muse Spark Open，四台 Mac Studio 集群可实现每秒 36 tokens 以上的生成速度，超过人类平均阅读速度。单台 Mac Studio 最高支持 512GB 统一内存，多台可通过 Thunderbolt 的 RDMA 驱动扩展。

正文

Not exactly your average "desk", but still neat.

  In this post, we show how to run the latest frontier-class model — Muse Spark Open, with nearly a trillion parameters — right from your desk, using the latest version of MLX, released today. On a cluster of four Mac Studios, Muse Spark Open generates over 36 tokens per second (see Figure 1), well above average human reading speed. Beginning on a single Mac Studio (up to 512GB of unified memory), then scaling out across multiple Macs with the RDMA over Thunderbolt driver, below we share an overview of the range of models you can now run on Mac Studio.

来源：Hacker News · 首页 · news.ycombinator.com