Meta has worked with Apple to bring its large Muse Spark Open AI model to M5 Ultra Mac Studios, letting developers run advanced AI locally instead of relying on cloud servers. Announced on October 15, Muse Spark Open is an open-weight model designed for coding, software engineering, and tasks that require multiple steps. Meta developed the model with 816 billion parameters, although only 42 billion are active during processing.
Running the model requires at least two M5 Ultra Mac Studios with 512GB of unified memory each, or four machines configured with 256GB each, using hardware introduced in Apple's recent Mac Studio refresh. The four-machine configuration is available now, but Apple's 512GB option isn't expected to ship until late October. The collaboration takes advantage of Apple's unified memory architecture, which allows the CPU and GPU to access the same memory pool. Even that much memory isn't enough for Muse Spark Open on a single machine, since the model's compressed weights occupy approximately 493GB before accounting for the memory required during processing.
The open-source MLX framework distributes the workload across multiple Macs, which communicate using Thunderbolt 5 and remote direct memory access, or RDMA. In Apple's benchmarks, four M5 Ultra Mac Studios generated more than 36 tokens per second with an 8,192-token context. Actual performance depends on the workload and context length, but the results suggest the model can deliver responses at a practical speed.
Meta demonstrated the model handling several complex workflows entirely on local hardware. Using its Muse Code development tool, the model modified Ice Cubes, an open-source Mastodon client for iOS, fixing bugs, adding features, and completing a build. Another demonstration showed Muse Spark Open controlling Da Vinci Resolve to review video footage and crop useful segments into vertical clips. These demonstrations show specific tasks being completed but don't establish how reliably the model performs across other workflows.
Source: AppleInsider · Summarized by HeadlinesBriefing