
That gap is precisely what the collaboration is intended to address, said Rachita Rao, senior analyst at Everest Group. “This is a mainframe adjacency play,” she said. “The intent is to extend IBM Z and LinuxONE environments by enabling Arm-compatible workloads to run closer to systems of record. While hyperscalers use Arm to lower their own internal power costs and pass savings to cloud-native tenants, IBM is targeting the sovereign and air-gapped market.”
For banks and insurers specifically, the collaboration is as much about people as it is about technology, Rao said. “These organizations are hesitant to change architectures due to the risk of breaking the ledger, but they face a shrinking pool of legacy specialists,” she said. “It doesn’t change the procurement cycle today, but it de-risks the long-term viability of the LinuxONE or the Z platform as a modern internal cloud.”
The chips behind it
The collaboration involves two hardware platforms built by IBM to handle AI workloads at mainframe scale: the Telum II processor and the Spyre Accelerator.
The Telum II processor, announced at Hot Chips in August 2024, has eight cores running at 5.5GHz, a 40% larger on-chip cache at 360MB, a built-in AI accelerator for real-time transaction inferencing, and a new data processing unit for IO tasks, IBM said.
The Spyre Accelerator is now shipping as part of the IBM z17 and LinuxONE 5 platforms. It connects via PCIe, has 32 compute cores, up to 1TB of memory per IO drawer, and draws no more than 75 watts per card, IBM said. The two chips work together to run ensemble AI, where multiple AI models are combined to produce more accurate results, according to IBM.
No timeline yet
IBM gave no shipping date and no technical specs for the planned dual-architecture systems. Statements on future direction “represent goals and objectives only” and are subject to change, the announcement said.





















