Skip to main content Tech Radar Pro Tech Radar Gaming Tech Radar Pro TechRadar the business technology experts Search TechRadar View Profile België (Nederlands) Deutschland North America US (English) Australasia New Zealand Expert Insights Website builders Web hosting Best web hosting Best website builder Best office chairs Expert Insights Intel's former CEO puts money into a little-known hardware startup that wants to make Nvidia obsolete Wayne Williams 8 April 2025 UK-based Fractile, also backed by NATO, says it can run LLMs 100x faster When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works. (Image credit: Fractile) UK-based Fractile is backed by NATO and wants to build faster and cheaper in-memory AI compute Nvidia's bruteforce GPU approach consumes too much power and is held back by memory Fractile's numbers focused on a cluster of H100 GPU comparison, not the mainstream H200 Nvidia sits comfortably at the top of the AI hardware food chain, dominating the market with its high-performance GPUs and CUDA software stack, which have quickly become the default tools for training and running large AI models - but that dominance comes at a cost - namely, a growing target on its back. Hyperscalers like Amazon, Google, Microsoft and Meta are pouring resources into developing their own custom silicon in an effort to reduce their dependence on Nvidia’s chips and cut costs. At the same time, a wave of AI hardware startups is trying to capitalize on rising demand for specialized accelerators, hoping to offer more efficient or affordable alternatives and, ultimately, to displace Nvidia. You may not have heard of UK-based Fractile yet, but the startup, which claims its revolutionary approach to computing can run the world’s largest language models 100x faster and at 1/10th the cost of existing systems, has some pretty noteworthy backers, including NATO and the former CEO of Intel, Pat Gelsinger. You may like A look at the unbelievable Nvidia GPU that powers DeepSeek's AI global ambition I am thrilled by Nvidia’s cute petaflop mini PC wonder, and it’s time for Jensen’s law: it takes 100 months to get equal AI performance for 1/25th of the cost Removing every bottleneck “We are building the hardware that will remove every bottleneck to the fastest possible inference of the largest transformer networks," Fractile says. "This means the biggest LLMs in the world running faster than you can read, and a universe of completely new capabilities and possibilities for how we work that will be unlocked by near-instant inference of models with superhuman intelligence.” It’s worth pointing out, before you get too excited, that Fractile’s performance numbers are based on comparisons with clusters of Nvidia H100 GPUs using 8-bit quantization and TensorRT-LLM, running Llama 2 70B - not the newer H200 chips. In a LinkedIn posting, Gelsinger, who recently joined VC firm Playground Global as a General Partner, wrote, “Inference of frontier AI models is bottlenecked by hardware. Even before test-time compute scaling, cost and latency were huge challenges for large scale LLM deployments... To achieve our aspirations for AI, we will need radically faster, cheaper and much lower power inference.” Are you a pro? Subscribe to our newsletter Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed! Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over. “I’m pleased to share that I’ve recently invested in Fractile, a UK-founded AI hardware company who are pursuing a path that’s radical enough to offer such a leap," he then revealed. "Their in-memory compute approach to inference acceleration jointly tackles the two bottlenecks to scaling inference, overcoming both the memory bottleneck that holds back today’s GPUs, while decimating power consumption, the single biggest physical constraint we face over the next decade in scaling up data center capacity. In fact, some of the ideas I was exploring in my graduate work at Stanford University will now come to mainstream AI computing!” You might also like Bye Nvidia! Meta tests its first in-house training AI-PU TSMC, Broadcom could tear apart Intel's legendary business after 57 years Nvidia is dreaming of trillion-dollar data centres with millions of GPUs Wayne Williams Social Links Navigation Wayne Williams is a freelancer writing news for TechRadar Pro. He has been writing about computers, technology, and the web for 30 years. In that time he wrote for most of the UK’s PC magazines, and launched, edited and published a number of them too. You must confirm your public display name before commenting Please logout and then login again, you will then be prompted to enter your display name. A look at the unbelievable Nvidia GPU that powers DeepSeek's AI global ambition I am thrilled by Nvidia’s cute petaflop mini PC wonder, and it’s time for Jensen’s law: it takes 100 months to get equal AI performance for 1/25th of the cost Nvidia, look away! OpenAI is almost ready to deliver first prototype of its AI GPU - General Processing Unit DeepSeek on steroids: Cerebras embraces controversial Chinese ChatGPT rival and promises 57x faster inference speeds Tech startup proposes a novel way to tackle massive LLMs using the fastest memory available to mankind Nvidia calls DeepSeek an 'excellent AI advancement' and praises the Chinese AI app's ingenuity Latest in Pro Google Cloud Next 2025 — all the news and updates as it happens Ancient flaw that allowed hackers to view your Chrome browser history has finally been patched, so update now US senators seek answers on Google and Microsoft AI deals which may 'discourage competition' Court confirms Apple is suing UK government over encryption backdoor request WhatsApp patches worrying vulnerability which allowed hackers to share .exe files as images Huawei's journey may be the blueprint for a post-Trump, non-US centric technology world Latest in News Uh oh, Nintendo Switch 2 pre-orders have reportedly now been delayed in Canada too Hades 2 will be a Nintendo Switch and Switch 2 exclusive at launch, but don't worry it's still coming to other platforms later Apple TV’s new Android app just got two great updates, but it’s still missing a big feature Hulu's back after being down for many – here's everything we know Google Cloud Next 2025 — all the news and updates as it happens Audio-Technica’s limited-edition $199 gold turntable is the reason I’ll be waiting in line at 8am on Record Store Day More about pro US senators seek answers on Google and Microsoft AI deals which may 'discourage competition' CrushFTP vulnerability exploited in the wild, added to CISA KEV database US senators seek answers on Google and Microsoft AI deals which may 'discourage competition' See more latest Most Popular US senators seek answers on Google and Microsoft AI deals which may 'discourage competition' CrushFTP vulnerability exploited in the wild, added to CISA KEV database Google Cloud Next 2025 — all the news and updates as it happens Hades 2 will be a Nintendo Switch and Switch 2 exclusive at launch, but don't worry it's still coming to other platforms later Turkey wants to make it easier for authorities to block social media and messaging apps Uh oh, Nintendo Switch 2 pre-orders have reportedly now been delayed in Canada too The Last of Us season 2 cast and character guide: who's playing who in the popular HBO TV show's next chapter? Apple TV’s new Android app just got two great updates, but it’s still missing a big feature This trick could allow you to upgrade an AMD RX 9070 GPU to be an RX 9070 XT for free, in theory – but I’d seriously advise against it New White House directive lifts AI safeguards in the name of modernization LATEST ARTICLES US senators seek answers on Google and Microsoft AI deals which may 'discourage competition' CrushFTP vulnerability exploited in the wild, added to CISA KEV database Fujifilm GFX100RF vs Leica Q3: I compared two of the best compact cameras money can buy, and I have a surprising favorite Google Cloud Next 2025 — all the news and updates as it happens Hades 2 will be a Nintendo Switch and Switch 2 exclusive at launch, but don't worry it's still coming to other platforms later TechRadar is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site. Contact Future's experts Terms and conditions Privacy policy Cookies policy Advertise with us Web notifications Accessibility Statement Future US, Inc. Full 7th Floor, 130 West 42nd Street, Please login or signup to comment Please wait...