{"id":144378,"date":"2026-08-19T02:38:20","date_gmt":"2026-08-19T02:38:20","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/144378\/"},"modified":"2026-08-19T02:38:20","modified_gmt":"2026-08-19T02:38:20","slug":"cerebras-says-latest-offering-is-fastest-ai-accelerator-in-the-industry-as-it-takes-aim-at-nvidia","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/144378\/","title":{"rendered":"Cerebras says latest offering is ‘fastest AI accelerator in the industry’ as it takes aim at Nvidia"},"content":{"rendered":"\n

The competition is heating up for Nvidia (NVDA<\/a>), as AI chipmaker Cerebras (CBRS<\/a>) unveiled its newest rack-scale system, which it claims offers 30x the tokens per second per user compared with graphics processing units. <\/p>\n

Called the Cerebras CS-4, the system packs three wafer-scale WSE-3 Turbo processors, which the company says are the largest AI semiconductors ever built, packing 4 trillion transistors. <\/p>\n

Cerebras’ systems are designed for AI inference, running AI models, rather than training them. They use a kind of memory called static random-access memory (SRAM) rather than dynamic random-access memory (DRAM). <\/p>\n

SRAM is far faster than DRAM, but much more complex, making it larger and more expensive than DRAM. That makes using SRAM all but impossible with your average pint-sized processor. <\/p>\n

\"A<\/a> The Cerebras CS-4 rackscale system. \u00b7 Cerebras <\/p>\n

Cerebras’ dinner plate-sized wafers provide the space needed to leverage SRAM. <\/p>\n

What’s more, the fact that Cerebras’ processors are a single product means data has to travel shorter distances than, say, Nvidia or AMD’s systems, which pair multiple chips that have to move data around more. <\/p>\n

“Historically, fast inference meant using smaller and less capable models. Cerebras CS-4 delivers industry-leading speeds on the largest frontier models, fundamentally changing the paradigm,” Cerebras CEO Andrew Feldman said in a statement. <\/p>\n

“Every aspect of the design has been optimized to deliver the highest speeds with massive throughput.\u00a0 With the CS-4, AI is so fast that it fundamentally reshapes product experiences,” he added. <\/p>\n

In addition to its hardware, Cerebras also hosts its own AI cloud services running on the chips that it rents out to customers. <\/p>\n

Cerebras went public in May at $185 per share and began trading at $350, but it has fallen precipitously since then. Shares were down more than 35% to $218 as of midday Tuesday. <\/p>\n

The company’s Q2 earnings results didn’t help things either, as the company reported a loss per share of -$2.98 versus a profit of $1.91 in the same quarter last year.\u00a0 <\/p>\n

And while the company offered better-than-anticipated Q3 guidance, it wasn’t enough to impress investors on Wall Street. <\/p>\n

\"A<\/a> Sign up for Yahoo Finance’s Week in Tech newsletter. \u00b7 Yahoo Finance <\/p>\n

Email Daniel Howley at dhowley@yahoofinance.com. Follow him on X at @DanielHowley<\/a>. <\/p>\n

Click here for the latest technology news that will impact the stock market<\/a>. <\/p>\n

Read the latest financial and business news from Yahoo Finance<\/a> <\/p>\n