Title
Description
Apple silicon: Made for AI
Apple silicon chips can more efficiently handle AI inference tasks, making every Apple silicon-powered device AI-ready. Use them to build models, apps, user platforms, and more.
High-performance CPU & GPU
Apple silicon chips feature high-performance CPU cores. And the GPU is optimized for parallel processing, allowing it to better handle AI workloads.
Dedicated neural engine
Designed specifically for machine learning, the dedicated Neural Engine is extremely efficient for AI inference tasks such as image recognition and natural language processing.
Advanced acceleration
Specialized machine learning accelerators offload AI tasks from the CPU and GPU, improving overall efficiency and speed.
Unified memory
The unified memory architecture allows the CPU, GPU, and Neural Engine to share the same memory pool, allowing them all to work faster and more efficiently.
Complete optimization
Because Apple has designed both the hardware and software on a Mac, AI tools can be finely tuned to make the most of the available resources.
Popular AI tools work on macOS
The ultimate AI business intelligence tool. Any LLM, any document, full control, full privacy
Learn moremacOS AI Resources
Create ML Overview
Experience an entirely new way of training machine learning models on your Mac. Create ML takes the complexity out of model training while producing powerful Core ML models.
Core ML
Use Core ML to integrate machine learning models into your app. Core ML provides a unified representation for all models. Your app uses Core ML APIs and user data to make predictions, and to train or fine-tune models, all on a person's device.
Machine Learning
Create intelligent features and enable new experiences for your apps by leveraging powerful on-device machine learning. Learn how to build, train, and deploy machine learning models into your iPhone, iPad, Mac, and Apple Watch apps.
MLX: An array framework for Apple silicon
MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon, brought to you by Apple machine learning research.
The Python API closely follows NumPy with a few exceptions. MLX also has a fully featured C++ API which closely follows the Python API.
Open ELM: An efficient language model family with open training and inference framework
OpenELM uses a layer-wise scaling strategy to efficiently allocate parameters within each layer of the transformer model, leading to enhanced accuracy.
For this workload
Description
Works with what you already use
Ready?
Description