An Intellyx Brain Candy Brief
Neural processing units (NPUs) complement central processing units (CPUs) and graphics processing units (GPUs) on AI-centric devices including most modern smartphones.
As part of each smartphone’s system-on-a-chip architecture, NPUs handle AI tasks requiring less power (and thus generating less heat) than GPUs.
OptAI leverages smartphones’ NPUs to compress and accelerate LLMs so that the devices can run the models internally without the need for cloud connectivity.
With OptAI, Even the most processor-intensive AI applications can run on phones without generating excessive heat.
Customers can choose the model. Today, OptAI supports common public models with fine-tuned specialized language models (SLMs) in the works.
Copyright © Intellyx BV. Intellyx is an industry analysis and advisory firm focused on enterprise digital transformation. Covering every angle of enterprise IT from mainframes to artificial intelligence, our broad focus across technologies allows business executives and IT professionals to connect the dots among disruptive trends. None of the vendors mentioned in this article is an Intellyx customer. No AI was used to produce this article. To be considered for a Brain Candy article, email us at pr@intellyx.com.
