TPUs: Google's home advantage
How does TPU v7 stack up against Nvidia's latest chips – and can Google scale AI using only its own supply?
In the race to train and deploy generative AI models, companies have poured hundreds of billions of dollars into GPUs, chips that have become essential for the parallel processing needs of large language models.
Nvidia alone has forecast $500 billion in sales across 2025 and 2026, driven largely by Jensen Huang, founder and CEO at Nvidia, recently stated that “inference has become the most compute-intensive phase of AI — demanding real-time reasoning at planetary scale”.
Google is meeting these demands in its own way. Unlike other firms reliant on chips by Nvidia, AMD, and others, Google has long used its in-house ‘tensor processing units’ (TPUs) for AI training and inference.
What are the benefits and drawbacks of Google’s reliance on TPUs? And how do its chips stack up against the competition?
In this episode, Jane and Rory discuss TPUs – Google’s specialized processors for AI and ML – and how they could help the hyperscaler outcompete its rivals.
Highlights
“So one of the main advantages of TPUs for Google is that it designs them, it has them manufactured through TSMC, which means it has sole dibs on them. This avoids a lot of the supply chain bottlenecks we've seen in recent years where companies have been queuing up for Nvidia chips. Nation states have been queuing up for Nvidia chips, or they've been forced to buy them in massive quantities up front and then slowly figure out where they're going to deploy them all.”
“Nvidia really is setting the standard on enterprise AI hardware. Like you said, Intel, AMD are also major players in the space and they have their chunk of the market, but Nvidia is the one that the major AI developers come back to again and again. It's making the hundred billion dollar announcements, all of this investment that seems to be announced every month.”
Sign up today and you will receive a free copy of our Future Focus 2026 report - the leading resource for IT decision-maker insight on priorities and investment areas in AI, security and more.
“It's a trade off for Google, because what you're doing is throwing a lot more compute at one workload, but potentially you're sacrificing some latency there. So all of that is to say that it's not as simple as just bigger numbers are better here. It really depends on the workload. But it's clear that, particularly with the latest iteration of TPUs, Google is seriously contending with the raw performance that companies like Nvidia can offer.”
“I'd say at this point it's clear that we haven't quite hit the wall that maybe some people were predicting earlier in the year, where people were saying it's incremental returns, if you just increase the size of the model – and maybe we do need to go back to the drawing board. I think Gemini 3 Pro shows that, at least for now, there is some life in just scaling things and seeing how much performance we can squeeze out of them.”
Footnotes
- What is a tensor processing unit (TPU)?
- ‘TPUs just work’: Why Google Cloud is betting big on its custom chips
- Google boasts that a single Gemini prompt uses roughly the same energy as a basic search – but that’s not painting the full picture
- Google Cloud announces major computing boost with Ironwood chip, new hypercomputer upgrades
- Google claims its AI chips are ‘faster, greener’ than Nvidia’s
Subscribe
- Subscribe to The IT Pro Podcast on Apple Podcasts
- Subscribe to The IT Pro Podcast on Spotify
- Subscribe to the IT Pro newsletter
- Join us on LinkedIn
Rory Bathgate was Features and Multimedia Editor at ITPro until 2026, overseeing all in-depth content and case studies. He also co-hosted the ITPro Podcast with Jane McCallion, swapping a keyboard for a microphone to discuss the latest learnings with thought leaders from across the tech sector.
In his free time, Rory enjoys photography, video editing, and good science fiction. After graduating from the University of Kent with a BA in English and American Literature, Rory undertook an MA in Eighteenth-Century Studies at King’s College London. He joined ITPro in 2022 as a graduate, following four years in student journalism. You can contact Rory on LinkedIn.
-
What is a flatpack data center?Podcast Is this a cheaper and more environmentally friendly way to operate a data center?
-
The Google Cloud outage explained: What happened, who was affected, and what can we learn from the incident?News The eight-hour Google Cloud outage hit a range of organizations including banks and delivery services
-
SPECIAL EDITION: Future-proofing the modern enterprise in an AI-centered worldSponsored podcast The Global Chief Technology Officer and Chief AI Officer of Dell Technologies, John Roese, discusses the Modern Enterprise Readiness Report and how businesses can close the execution gap.
-
Have agents, copilots, and chatbots made life harder?Podcast AI was meant to lighten the load and help workers carry out tasks without having to learn new skills – in reality, that's not quite what happened
-
SPECIAL EDITION: Scaling, ROI, and what’s next for workplace AIAgents and productivity may be taking center stage, but there’s more to enterprise AI than the tech
-
SPECIAL EDITION: What enterprises need from a modern data centerPodcast We talk to Dell Technologies about the evolution of the modern data center
-
Rogue AI and unionization at MetaPodcast Bobby Hellard, Scott Bekker, and Ross Kelly look at the recent spate of AI agent hacks and Meta’s deal with Prospect
-
Dreamforce 2026 and the dangers of AIPodcast Ross Kelly joins us from San Francisco to talk AI safety, Claudforce, Koa, and all things Dreamforce