Apple and Meta are collaborating so that Meta’s Muse AI model can run directly on Mac computers.
The model at the center of the partnership is Muse Spark Open, which Meta unveiled on October 15, 2026. Meta presents it as the most advanced open-weight AI model built in the United States. It can run entirely on Apple hardware, with no cloud server involved.
What Muse Spark Open actually is
Start with size. Muse Spark Open carries 816 billion parameters, and 42 billion of them are active at any given time.
The model is natively multimodal, so it was built from the start to handle more than plain text. It also has a context window of 1 million tokens.
Meta says the model is tuned for agentic work. That covers coding, long-horizon workflows and multi-step reasoning.
The weights are available through several major platforms, including Hugging Face and Amazon SageMaker.
Where the Mac comes in
Running an 816 billion parameter model usually calls for a data center. Muse Spark Open can instead run on two Apple M5 Ultra Mac Studios linked together.
The setup relies on Apple’s MLX framework, a software toolkit for machine learning on Apple chips. MLX lets the two machines behave like a single computer. Together they pool nearly 1 terabyte of unified memory.
The result is a model that runs locally, with no dependence on cloud services.
Meta showed off what that looks like in practice. One demo used the model to make automated changes to iOS applications. Another ran video editing workflows in DaVinci Resolve entirely on-device.
Earlier Muse models, such as the smaller Muse Glimmer, also had open weights. What sets Spark Open apart is its emphasis on high-end local deployment on Apple machines.
Building out the Muse ecosystem
Muse Spark Open isn’t arriving alone. It extends Meta’s broader Muse AI agent lineup, which already includes a native Mac app.
Meta launched its Muse personal AI agent on September 8, 2026, roughly five weeks before Spark Open. That agent performs tasks across native macOS apps, operating within permissions the user controls.
The sequence tells a story. Meta first released the smaller open-weight Glimmer, then put a personal agent on the Mac, and now offers a frontier-scale model that runs on Apple hardware.
What this means for Apple, Meta and the AI race
For Apple, the partnership is a strong advertisement for its silicon. Running a model of this size on two desktop machines demonstrates on-device AI at frontier scale.
For Meta, the move reinforces its bet on open weights. Rivals that keep their best models locked behind cloud APIs force customers to send data out and pay per use. Meta is offering a different deal: take the model and run it yourself.
There are practical limits. Two top-tier Mac Studios are not a casual purchase, so this is a professional and enterprise tool rather than something for the average laptop owner.
Developers can already pull the weights from Hugging Face and Amazon SageMaker and test the claims themselves.
Disclosure: This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our Editorial Policy.