Meta launches an open-weight AI model that runs on Macs
Meta and Apple have teamed up for the launch of the social media giant's newest model, Muse Spark Open, which will run locally on Apple silicon.
Key points
- Meta launched Muse Spark Open, an open-weight AI model designed to run locally on Macs.
- The model has 816 billion parameters and a 1 million token context window.
- Running it locally requires at least 1 terabyte of RAM, best on a Mac Studio with M5 Ultra.
Meta has launched Muse Spark Open, which it calls the most capable open-weight AI model in the United States. The model was also designed to work with Macs, according to evaluation results Meta released on Thursday.
Muse Spark Open uses 816 billion parameters and a 1 million token context window. Meta claims it outperforms other popular open-weight models.
Local Mac requirements
The model is natively multimodal and built for complex coding tasks and agentic labor. It can run locally on Apple computers, but requires at least 1 terabyte of RAM, per Engadget. Meta says it runs best on a Mac Studio with the M5 Ultra chip.
Coding and video tests
Meta paired the model with Muse Code, its AI coding terminal, and used it in agentic workflows. These included coding fixes for a Mastodon client, covering bug fixes, new features and a full build. Meta also said the model was used to review and crop footage in DaVinci Resolve, a high-end video editing program.
Availability and open-weight benefits
Meta is making Muse Spark Open available now through several API platforms. The company says open-weight models can be more cost-efficient and offer transparency and flexibility that closed, proprietary models do not.
