Oracle and Google are partnering to enable Oracle to offer Google’s Tensor Processing Units (TPUs) from Oracle Cloud Infrastructure (OCI).

Oracle will deploy the TPUs within its data center infrastructure, making it the first hyperscaler to adopt the chips since Google announced in April 2026 that it would be offering its chips for sale to a “select group of customers.”

“Different AI workloads have different compute needs,” said Mahesh Thiagarajan, president, Oracle Cloud Infrastructure, Oracle. “Bringing Google TPUs to OCI gives customers access to multiple leading AI compute architectures in one cloud. That choice gives them the flexibility to choose the right infrastructure for the performance, throughput, and economics of each AI workload.”

Google is currently on its eighth generation of TPUs, having spent more than a decade developing the chips. The TPU 8t is designed for training and can deliver nearly 3x the compute performance per pod over the previous generation, while TPU 8i is an inference chip designed to handle the iterative work of many specialized agents.

TPU 8t has 19.2Tbps of bidirectional scale-up bandwidth and 400Gbps of scale-out networking bandwidth, with Google introducing a new networking architecture to support the hardware. Called Virgo Network, the company claims it supports a 4x increase in data center bandwidth and has been built on high-radix switches that reduce network layers.

Meanwhile, designed with more memory bandwidth to serve latency-sensitive inference workloads, the TPU 8i is scalable to 1,152 chips in a single pod. It delivers 11.6 exaflops of FP8 compute performance, with a total HBM capacity of 331.8TB per pod and 19.2Tbps of bidirectional scale-up bandwidth per chip.

While Oracle declined to comment on the scale of the initial deployment, Karan Batta, SVP of Oracle Cloud Infrastructure, told DCD at the Oracle AI World event in Las Vegas that it would be a “multi-year, multi-gigawatt partnership with Google and it will look and feel the same as it does from a GCP standpoint.”

He added: “What I can tell you is that this is not an experiment. This is going to be a cloud gigawatt-scale investment from Oracle over time, and the best way to think of it is that when Google launches a new TPU, we will have it on day one.”

Google TPUs on OCI will be available in calendar year 2027, ramping over a multi-year period to meet customer needs.

Google is also working with Blackstone to create a US-based cloud platform offering Google's Tensor Processing Units (TPUs). Depending on which launches first, Oracle could be the first to bring online the TPUs outside of Google's platform.