Spyre Accelerator
IBM's PCIe AI inference card. On IBM Power 11 it carries 32 cores, 128 GB of memory, and more than 300 TOPS inside a 75 watt envelope.
The Spyre Accelerator is IBM's commercial AI inference card, built on a 5 nm process with 25.6 billion transistors and 128 GB of LPDDR5 memory. It became generally available for IBM z17 and LinuxONE 5 on October 28, 2025 and for Power 11 in December 2025. On IBM Power it installs in an ENZ0 PCIe4 expansion drawer, up to 16 cards per system, and IBM lists Red Hat AI Inference Server or Red Hat OpenShift AI on Red Hat Enterprise Linux 9.6, 9.8, or 10.2 as required software. It is not an IBM i native device: the card is driven from a Linux partition on the same physical server.
Related Terms
Matrix Math Acceleration (MMA)
An on-chip acceleration feature in IBM Power10 and Power11 processors that speeds up the matrix math operations used in AI inferencing, without requiring a separate GPU.
ENZ0 Expansion Drawer
The PCIe4 expansion drawer IBM documents for supported Spyre Accelerator for Power configurations on Power 11 systems.
Red Hat AI Inference Server
Red Hat's model serving product, built on the open source vLLM engine. IBM lists it as one of two supported ways to drive a Spyre Accelerator on IBM Power.
Artificial Intelligence Unit
The IBM Research prototype chip that became the commercial Spyre Accelerator. Thirty-two cores, never sold.