Can I run an LLM on the device itself
Asked on 08/11/2024
1 search
Yes, you can run a large language model (LLM) on the device itself using Apple's platforms. Apple provides tools and frameworks such as Core ML to facilitate the deployment and execution of machine learning models on their devices. You can start with a model developed in PyTorch, convert it to the Core ML format using Core ML tools, and then integrate it into your app. Core ML optimizes the model for hardware-accelerated execution across the CPU, GPU, and neural engine, making it possible to run models like Whisper, Stable Diffusion, and Mistral on Apple devices.
For more details on running models on device, you can refer to the session Explore machine learning on Apple platforms (07:16).

Explore machine learning on Apple platforms
Get started with an overview of machine learning frameworks on Apple platforms. Whether you’re implementing your first ML model, or an ML expert, we’ll offer guidance to help you select the right framework for your app’s needs.

Platforms State of the Union
Discover the newest advancements on Apple platforms.

Bring your machine learning and AI models to Apple silicon
Learn how to optimize your machine learning and AI models to leverage the power of Apple silicon. Review model conversion workflows to prepare your models for on-device deployment. Understand model compression techniques that are compatible with Apple silicon, and at what stages in your model deployment workflow you can apply them. We’ll also explore the tradeoffs between storage size, latency, power usage and accuracy.