Google announced the expansion of its eighth-generation TPU portfolio with two additional systems, TPU 8i Max and TPU 8tx. Specializing in secure, high-context AI, each system targets a distinct part of the AI lifecycle. This marks the first time Google has introduced four TPU configurations in a single year.
Google uses TPUs in many different ways: to train and serve its own Gemini models, to take on agentic workloads ; to deliver services to Google Cloud customers on its own cloud infrastructure; and more recently, following increased interest and demand, to allow customers to deploy them directly in their own data centers. This has made TPUs a rapidly growing business with nearly 100 customers – including frontier labs, trading firms, retailers, universities, and more.
First announced at Cloud Next in April 2026, TPU 8t and TPU 8i established the baseline for this generation of chips and offer up to 2.7 times better training performance and 80% better inference price performance, respectively, vs. previous generations of TPUs. TPU 8t was designed to be a training powerhouse for massive foundation models with maximum “goodput” — or the useful intelligence delivered per watt of energy used. TPU 8i is the reasoning engine, designed to break the memory wall, cutting inter-chip communication delays by up to half. Now, as enterprises bring autonomous agents into production, Google has created two new configurations of these foundational systems – TPU 8i Max and TPU 8tx – to solve two urgent new challenges: hardware-level data security and million-token context scale.
“With computing moving from human to agent scale, businesses are asking for accelerators that can reason across AI models’ massive context windows. In addition, some highly regulated customers are asking for specialized encryption capabilities for unique workloads,” said Amin Vahdat, Chief Technologist and Senior Vice President for AI and Infrastructure at Google. “These new TPU systems address this new reality. Coupled with our recent PyTorch announcements, our aim is to bring TPUs more easily accessible to every developer and every customer. By combining modular custom silicon with an open, easy-to-use software stack, we can deliver new hardware and system configurations at the pace of the AI industry.”
TPU 8tx, optimized for confidential inference and small-scale training
TPU 8tx is built for regulated enterprises and governments running frontier or proprietary models and autonomous agents alongside their most sensitive data.
Normally, data is encrypted when stored or sent over a network, but has to be unlocked in memory while a computer processes it. Built on the same silicon as TPU 8t and paired with custom AMD CPU hosts, TPU 8tx builds security directly into the hardware layer, keeping sensitive data and model weights protected and isolated even while in active use. And by adopting the same low-latency Boardfly network that was created for real-time reasoning, TPU 8tx keeps multi-step agents moving, delivering 2x lower latency compared to TPU 8t with a near-zero performance penalty.
Pairing training-grade compute with a fast inference network also means organizations can simultaneously run and customize their models on a single system. TPU 8tx enables teams to fine-tune models using their private data, distill large models into smaller ones, and train their agents through reinforcement learning, all without needing to migrate sensitive data between separate clusters.
TPU 8i Max, built to address the memory wall
When dozens of AI agents work together across an entire software codebase or hours of video at once, memory bandwidth quickly becomes the bottleneck.
TPU 8i Max scales compute and memory in lockstep, delivering double the compute, double the SRAM and double the HBM bandwidth of TPU 8i, so processors remain equipped with essential data and so that large workloads do not stall. Further, because TPU 8i Max fits twice the silicon within the existing rack footprint, data centers can deploy significantly more computing power per square foot and per watt.
While flexible across workloads, together the four systems in Google’s eighth-generation TPUs give customers a purpose-built accelerator for every stage of the agentic lifecycle. TPU 8t for scale-up training, TPU 8i for low-latency reasoning, TPU 8tx for confidential computing, and TPU 8i Max for massive context windows and the highest compute density per rack.
Gartner unveils Top 10 Strategic Technology Trends for 2027
Roblox names Joel Neoh Managing Director for Southeast Asia and Oceania
