IBM has announced the release of its latest mainframe hardware, the z17, which is specifically designed to accelerate artificial intelligence (AI) adoption in enterprises. The new mainframe is powered by the IBM Telum II processor and is capable of processing 450 billion inference operations per day, a 50% increase over its predecessor, the z16.

The z17 mainframe is fully encrypted and supports over 250 AI use cases, including AI agents and generative AI. This is significant, given that mainframes are still widely used by 71% of Fortune 500 companies today, with the mainframe market valued at an estimated $5.3 billion in 2024, according to Market Research Future.

Tina Tarquinio, VP of product management and design for IBM Z, revealed that the development of the z17 mainframe has been a five-year effort, with over 2,000 research hours spent gathering feedback from over 100 customers. Interestingly, the feedback received aligned with the current AI market trends, which have accelerated significantly since the release of OpenAI's ChatGPT in November 2022.

The z17 mainframe is designed to be highly adaptable and scalable, with the ability to integrate with other hardware, software, and open-source tools. It will support 48 IBM Spyre AI accelerator chips at launch, with plans to increase this number to 96 within the next 12 months. This built-in "headroom" will enable the mainframe to accommodate larger AI models and adapt to changing market demands.

One of the key highlights of the z17 mainframe is its energy efficiency, with Tarquinio claiming that it is more energy-efficient than its predecessor and competitors. The on-chip AI acceleration has increased by 7.5 times, while energy consumption has decreased by 5.5 times compared to other accelerators or platforms in the industry.

The z17 mainframe is set to become generally available on June 8, marking a significant milestone in IBM's efforts to accelerate AI adoption in enterprises. With its enhanced performance, scalability, and energy efficiency, the z17 is poised to play a critical role in shaping the future of AI in the enterprise.

As Tarquinio noted, the possibilities for AI are "really unlimited" and the z17 mainframe is designed to accommodate this uncertainty, providing a flexible and adaptable platform for businesses to explore the vast potential of AI. With the z17, IBM is well-positioned to capitalize on the growing demand for AI solutions and cement its leadership in the enterprise technology space.