In an attempt to attract business from artificial intelligence firms by providing custom silicon, Google is producing its most potent chip to date. The business announced on Thursday that Ironwood, the seventh iteration of its Tensor Processing Unit (TPU), first unveiled in April for testing and deployment, will be available for public use in the coming weeks.
Google has developed its own in-house chip designed to handle everything from training large AI models to powering real-time chatbots and AI agents. By connecting up to 9,216 chips in a single pod, the new Ironwood TPUs eliminate data bottlenecks for the most demanding models and enable customers to run and scale the largest and most data-intensive models available.
Google is competing fiercely with Microsoft, Amazon, and Meta to build the future of AI infrastructure. While most large language models and AI workloads currently rely on Nvidia’s GPUs, Google’s TPUs are custom-designed silicon that offer benefits in price, performance, and efficiency.
After a decade of development, the Ironwood TPU is over four times faster than its predecessor. Major customers are already on board — AI startup Anthropic plans to use up to one million of these chips to power its Claude model.
Also Read:
UPS Delivery Jet Crashed in Kentucky, Killing at Least Seven People
Mark Carney of Canada Pledges a “Bold” First Government Budget
