Oracle Cloud Infrastructure (OCI) is planning to launch a cluster of AMD Instinct MI450 Series GPUs with as many as 50,000 GPUs.

Set to become publicly available in Q3 2026 - and later be expanded in 2027 - the "supercluster" is the latest collaboration between AMD and Oracle.

The MI450 GPU will be based on the CDNA 5 architecture and made using TSMC's 2nm fabrication technology. Each GPU offers up to 432 GB of HBM4 and 20 TBps of memory bandwidth.

Speaking on the upcoming GPU, AMD's CEO Lisa Su told Yahoo Finance: "We are really excited about our MI450 generation, it has 2nm technology, so the most advanced fabrication capability, it has rack scale solutions, so we are really putting all of these compute elements together."

The cluster will use the AMD "Helios" rack design, including the MI450 GPUs, the next-generation AMD Epyc CPUs currently codenamed Venice, and the next-generation AMD Pensando networking system codenamed Vulcano.

Each GPU can be equipped with up to three 800Gbps “Vulcano” AI-NICs.

“Our customers are building some of the world’s most ambitious AI applications, and that requires robust, scalable, and high-performance infrastructure,” said Mahesh Thiagarajan, executive vice president, Oracle Cloud Infrastructure.

“By bringing together the latest AMD processor innovations with OCI’s secure, flexible platform and advanced networking powered by Oracle Acceleron, customers can push the boundaries with confidence. Through our decade-long collaboration with AMD - from Epyc to AMD Instinct accelerators - we’re continuing to deliver the best price-performance, open, secure, and scalable cloud foundation in partnership with AMD to meet customer needs for this next era of AI.”

“AMD and Oracle continue to set the pace for AI innovation in the cloud,” said Forrest Norrod, executive vice president and general manager for AMD's data center solutions business group. “With our AMD Instinct GPUs, Epyc CPUs, and advanced AMD Pensando networking, Oracle customers gain powerful new capabilities for training, fine-tuning, and deploying the next generation of AI. Together, AMD and Oracle are accelerating AI with open, optimized, and secure systems built for massive AI data centers.”

The latest collaboration follows just a few months after Oracle and AMD announced that the cloud provider would deploy a cluster with up to 131,072 of the AMD MI355X GPUs, building on the previously launched AMD Instinct MI300X cluster.

Earlier this month, AMD revealed it would be providing thousands of the chips to OpenAI - with the latter saying it will develop a 1GW data center with the GPUs in the second half of 2026.