Meta releases Muse Spark Open AI model optimised for Mac Studio

Meta has released Muse Spark Open, a large AI model designed to run locally on high-end Mac Studio computers, giving developers another option for running advanced AI tools without relying entirely on cloud services.

Announced on 15 October, the model has 816 billion total parameters, with 42 billion active parameters, and a context window of one million tokens. Meta says it is designed for demanding tasks including software engineering, coding and multi-step reasoning.

The model has been optimised to run on Apple Silicon using Apple's MLX machine-learning framework. Meta says two Mac Studio computers equipped with M5 Ultra chips can work together to run the model locally, using their combined memory capacity.

Running an AI model on a user's own hardware can offer greater control over how it is deployed and may reduce the need to send every task to a remote service. It can also allow developers to experiment with models and build their own applications around them.

There are practical limitations, however. The configuration described by Meta requires high-end hardware, making it a very different proposition from running a small AI model on an ordinary laptop. Local operation also does not automatically guarantee greater privacy for every application; that depends on how the software is configured and whether it sends information elsewhere.

Meta is releasing the model weights through platforms including Hugging Face and cloud-based model marketplaces. Developers can also customise the model, subject to the terms of its licence. Although the weights are available for wider use, the licence includes commercial conditions, so the release should not be described as unrestricted open-source software.

The launch is notable because it brings together Meta's model development and Apple's machine-learning tools, allowing a very large model to operate on desktop hardware. Meta says its testing has included software development tasks and workflows using DaVinci Resolve.

For developers and creative professionals, the release offers another way to explore locally run AI. Its accessibility will depend on hardware costs, performance and the licensing conditions attached to the model.