What is edge AI?

Copy URL

Edge artificial intelligence (AI), or AI at the edge, is the implementation of artificial intelligence in an edge computing environment, which allows computations to be done close to where data is actually collected, rather than at a centralized cloud computing facility or an offsite data center. Edge AI lets devices make smarter decisions faster, without connecting to the cloud or offsite data centers.

As edge computing brings data storage closer to the location of the device, AI algorithms process the data that are created on the device with or without having any internet connection. This allows data to be processed within milliseconds providing real-time feedback. Edge AI allows responses to be delivered almost instantly. This can be more secure when it means that some sensitive data never actually leaves the edge.

Due to their ability to move data away from overburdened cloud data centers, edge devices such as sensors and IoT devices are on their way to becoming key technologies.

Edge AI is different from the traditional AI application framework where the data generated by connected technologies is transmitted to a backend cloud system. Instead of running AI models at the backend, they are configured onto processors inside the connected devices operating at the network edge. This adds a layer of intelligence at the edge where the edge device not only collects metrics and analytics but is able to act upon them since there is an integrated machine learning (ML) model within the edge device making a true AI at the edge.

The goal of artificial intelligence stays the same — to build smart machines that work and perform tasks that humans normally do without human oversight. However, edge AI does the work and decision making locally, inside or near whatever device being used.

The combination of edge computing and artificial intelligence comes with great benefits. With edge AI, high-performance computing capabilities are brought to the edge, where sensors and IoT devices are located. Users can process data on devices in real time because connectivity and integration between systems isn’t required, and they can save time by aggregating data, without communicating with other physical locations.

The benefits of edge AI include: 

  • Less power use: Save energy cost with data processes at the local level with the power requirements for running AI at the edge being much lower than in cloud data centers
  • Reduced bandwidth: Reduce bandwidth in data flow and minimize costs with more data processed, analyzed, and stored locally instead of being sent to the cloud
  • Privacy: Lower the risk of misappropriated or mishandled data due with locally processed data on edge devices from edge AI operations
  • Security: Prioritizing important data transfer by processing and storing data in an edge network or filtering redundant, extraneous, and unneeded data
  • Scalability: Easily scale systems with cloud-based platforms and native edge capability on original equipment manufacturer (OEM) equipment 
  • Reduced latency: Take some of that load off the cloud platform and analyze locally to leave the cloud-based platform free for other tasks such as analytics

Red Hat does a lot of work on container and Kubernetes technologies with the greater open source community. Red Hat® OpenShift® brings together tested and trusted services to reduce the friction of developing, modernizing, deploying, running, and managing applications. 

Red Hat OpenShift includes key capabilities to enable machine learning operations (MLOps) in a consistent way across datacenters, hybrid cloud, and edge. With AI/ML on Red Hat OpenShift, you can accelerate AI/ML workflows and the delivery of AI-powered intelligent applications.

As an AI-focused portfolio, Red Hat OpenShift AI provides tools across the full lifecycle of AI/ML experiments and models and includes Red Hat OpenShift AI. It’s a consistent, scalable foundation based on open source technology for IT operations leaders while bringing a specialized partner ecosystem to data scientists and developers to capture innovation in AI.



InstructLab is an open source project for enhancing large language models (LLMs).

Keep reading


What is generative AI?

Generative AI relies on deep learning models trained on large data sets to create new content.


What is machine learning?

Machine learning is the technique of training a computer to find patterns, make predictions, and learn from experience without being explicitly programmed.


What are foundation models?

A foundation model is a type of machine learning (ML) model that is pre-trained to perform a range of tasks. 

More about AI/ML



A foundation model platform used to seamlessly develop, test, and run Granite family LLMs for enterprise applications.

An AI-focused portfolio that provides tools to train, tune, serve, monitor, and manage AI/ML experiments and models on Red Hat OpenShift.

An enterprise application platform with a unified set of tested services for bringing apps to market on your choice of infrastructure. 

Red Hat Ansible Lightspeed with IBM watsonx Code Assistant is a generative AI service designed by and for Ansible automators, operators, and developers. 



Top considerations for building a production-ready AI/ML environment

Analyst Material

The Total Economic Impact™ Of Red Hat Hybrid Cloud Platform For MLOps


Getting the most out of AI with open source and Kubernetes