Meta releases open-weight AI model that can run on Macs
Meta has launched Muse Spark Open, an open-weight AI model with 816 billion parameters. It is designed to run locally on Apple computers, though it requires at least 1 terabyte of RAM.
Technology company Meta announced a new open-weight artificial intelligence model, Muse Spark Open, on Thursday, October 15. The company calls it the "most capable" open-weight model in the United States. Open-weight models are those whose trained parameters are made available for others to use. The model is designed to run locally on Apple's Mac computers.
Capabilities and requirements
The model has 816 billion parameters and a context window of 1 million tokens. According to evaluation results Meta published, it outperforms other popular open-weight models. Muse Spark Open is natively multimodal and built for complex coding tasks and agentic work.
Running it locally takes substantial hardware: per Engadget, at least 1 terabyte of RAM is required. The model works best on a Mac Studio equipped with the M5 Ultra chip.
Trials
Meta says it paired the model with Muse Code, its AI coding terminal, and used it in various agentic workflows. These included coding work on a Mastodon client, covering bug fixes, new features and a full build. The company adds that it also used the model to operate DaVinci Resolve, professional video editing software, where it was able to review and crop footage.
Advantages of open-weight models
Open-weight models can be significantly more cost-efficient and offer transparency and flexibility that closed models do not allow. Meta is making the new model available now through several API platforms.
