Apple Macs Now Run Powerful AI Models Faster and Cheaper

A new software release, version 0.40.0, brings a significant change for Mac users with Apple Silicon chips (like M1, M2, or M3). Now, many AI models can run directly on your Mac using a technology called MLX, which is designed to take full advantage of Apple's hardware. This means you don't need to send your data to the cloud or rely on an internet connection to use AI. It's like having a powerful AI assistant built right into your computer.

The update adds support for several popular AI models, including Gemma 4, Qwen 3.6, and Qwen 3.5. These are large language models that can help with writing, coding, answering questions, and more. Previously, running such models on a personal computer was slow or impossible. With MLX, they run efficiently, so you get quick responses without waiting for data to travel to a server and back. This also means your conversations and data stay private on your device.

Additionally, decision models like Nimble, tev1, clef, and clef-flash are now available on MLX. These are specialized AI models that help make choices or predictions, often used in apps for recommendations or automation. By running them locally, apps can respond instantly and work offline. The developers plan to continue testing and adding more models, so the range of AI tools you can use on your Mac will keep growing.

For everyday users, this means your Mac can become a more powerful AI hub. You could use AI for writing emails, summarizing documents, or even generating images without worrying about subscription fees or data privacy. It also opens the door for developers to create smarter apps that work offline. While not all models are supported yet, this update is a big step toward making advanced AI accessible on personal devices, saving time and money while keeping your information secure.