AI on IBM Z

Unlock real-time AI insights with IBM Z

AI on IBM Z® brings real-time insights by applying machine learning directly to transactional data—eliminating the need for data movement.

Leveraging the advanced hardware and software stack of IBM z17, businesses can scale multiple AI models to power predictive use cases such as fraud detection and retail automation. With high throughput, low latency, and industry-leading cyber-resilience, IBM Z is built for mission-critical AI.

Discover AI activities reshaping banking automation

Speed to scale with transaction volume

With IBM z17, process up to 450 billion inference operations per day with 1 ms response time for real-time use cases.¹

Get real-time insights when needed

Infuse AI into every transaction—no data movement—while meeting the most stringent SLAs and response times.

Increased inference throughput

Route inference requests to any idle IBM Integrated Accelerator for AI to boost throughput up to 7.5x over IBM z16.²

Keep data secure and compliant

Run AI where your data already resides to safeguard sensitive information and support regulatory compliance.

Featured products

Unlock the potential of generative AI with IBM watsonx Code Assistant for Z and watsonx Assistant for Z . These tools enable hybrid or on-premise AI solutions, with future capabilities planned through the Spyre Accelerator³—expanding the reach of AI across your enterprise infrastructure.

watsonx Code Assistant for Z

A generative AI-powered tool that provides an end-to-end application developer lifecycle. It includes application discovery and analysis, automated code refactoring and COBOL to Java conversion.

AI Toolkit for Z and LinuxONE

Consists of IBM® Elite Support and IBM Secure Engineering. These vet and scan open-source AI, serving frameworks and IBM-certified containers for security vulnerabilities, and validate compliance with industry regulations.

Machine Learning for z/OS®

An AI solution for users to build machine learning models by using any platform of choice and deploy those models within transactional applications while maintaining SLAs.

IBM Synthetic Data Sets

A family of artificially generated datasets designed to enhance predictive AI model training and LLMs to benefit IBM Z enterprises in financial services to gain quick access to relevant and rich data for AI projects.

Related products

Conversational AI

Enables AI-powered virtual assistants on IBM Z, automating customer interactions with enhanced security and scalability. It combines conversational AI with the reliability of IBM Z for real-time enterprise support.

IBM watsonx Assistant for Z

AI-infused transactional data

Experience an agile, efficient and secure enterprise data serving for the most demanding hybrid cloud and transactional and analytics applications.

IBM Db2 for z/OS

Python AI Toolkit

Access a library of relevant open-source software to support current AI and machine learning workloads.

Python AI Toolkit for IBM z/OS®

Accelerate TensorFlow Inference

Bring TensorFlow models that are trained anywhere and deploy them close to your business-critical applications on IBM Z by using IBM Integrated Accelerator for AI.

IBM ZDNN Plug-in for TensorFlow

In-memory computing performance

Move forward with an in-memory compute engine and analytics run time that supports big-data languages such as JavaTM, Scala, Python and R.

IBM Z Platform for Apache Spark

Compile .onnx AI models into shared libraries

Compile compatible AI models into onnx format and run them on IBM Z with minimal dependencies, by using IBM Integrated Accelerator for AI seamlessly.

IBM Z Deep Learning Compiler

Popular open source tools

Use Anaconda on IBM Z and LinuxONE, and use industry-standard packages such as Scikit-learn, NumPy and PyTorch with cost-effective zCX containers.

Anaconda on IBM Z and LinuxONE

Demo video

AI on Linux with the IBM Integrated Accelerator for AI

Discover how you can run AI analysis with Linux on IBM Z systems. It can be done by using processor chips that are designed for AI making your analysis simpler, more secure and with real-time processing at scale.

Resources

Learn about the key elements of current and next-generation mainframes and how they are transforming the AI landscape.

Discover how mainframes are more relevant than ever for hybrid cloud optimization, AI innovation, and digital transformation.

Learn how to enable AI solutions in business-critical use cases, such as fraud detection and credit risk scoring, on the platform.

Discover low-latency AI on a highly trustworthy and secure enterprise system: the modernized IBM Mainframe.

Take the next step

Discover how to use AI and machine learning to convert data from every transaction into real-time insights.

Get started

More ways to explore

Documentation

Support

Lifecycle services and support

Community

Footnotes

¹ DISCLAIMER: Performance result is extrapolated from IBM® internal tests running on IBM Systems Hardware of machine type 9175. The benchmark was executed with 1 thread performing local inference operations using a LSTM based synthetic Credit Card Fraud Detection model (https://github.com/IBM/ai-on-z-fraud-detection) to exploit the Integrated Accelerator for AI. A batch size of 160 was used. IBM Systems Hardware configuration: 1 LPAR running Red Hat® Enterprise Linux® 9.4 with 6 IFLs (SMT), 128 GB memory. 1 LPAR with 2 CPs, 4 zIIPs and 256 GB memory running IBM z/OS® 3.1 with IBM z/OS Container Extensions (zCX) feature. Results may vary.

² DISCLAIMER: Performance results are based on internal tests exploiting the IBM Integrated Accelerator for AI for inference operations on IBM z16 and z17. On IBM z17, each IBM Integrated Accelerator for AI allows any CPU within a drawer to direct AI inference request to any of the 8 idle AI accelerators on the same drawer. The tests involved running inference operations on 8 parallel threads with batch size of 1. Both IBM z16 and z17 were configured with 2 GCPs, 4 zIIPs with SMT and 256 GB memory on IBM z/OS V3R1 with IBM Z Deep Learning Compiler 4.3.0, using a synthetic credit card fraud detection model (https://github.com/IBM/ai-on-z-fraud-detection). Results may vary.

³ Upon Spyre Accelerator availability. The IBM Spyre Accelerator is current in tech preview. https://www.ibm.com/docs/en/announcements/z17-makes-more-possible