IBM’s z17 is the latest generation mainframe, launched in April 2025 and engineered specifically for the AI era. At its core is the IBM Telum II processor, featuring an integrated AI accelerator that enables the system to handle over 450 billion AI inference operations per day with sub-millisecond response times—a 50% increase in AI performance over the previous z16 model. The z17 supports a wide range of AI workloads, including large language models and generative AI, and is designed for mission-critical, real-time applications such as fraud detection, customer service automation, and medical image analysis.

​

The mainframe also offers advanced security, scalability up to 208 cores and 64 TB of memory, and optional Spyre accelerators for even greater AI processing power, making it ideal for enterprises seeking robust, secure, and efficient AI solutions on-premises.