cd /news/ai-chips/cerebras-says-latest-offering-is-fas… · home topics ai-chips article
[ARTICLE · art-102201] src=ca.finance.yahoo.com ↗ pub= topic=ai-chips verified=true sentiment=· neutral

Cerebras says latest offering is 'fastest AI accelerator in the industry' as it takes aim at Nvidia

Cerebras Systems unveiled its CS-4 rack-scale AI inference system, claiming it delivers 30x the tokens per second per user compared with GPUs, as it competes with Nvidia. The CS-4 packs three wafer-scale WSE-3 Turbo processors with 4 trillion transistors, and Cerebras CEO Andrew Feldman said it 'delivers industry-leading speeds on the largest frontier models.' Shares of Cerebras, which went public in May at $185, were down more than 35% to $218 as of midday Tuesday after reporting a Q2 loss per share of -$2.98.

read2 min views5 publishedAug 19, 2026
Cerebras says latest offering is 'fastest AI accelerator in the industry' as it takes aim at Nvidia
Image: Ca (auto-discovered)

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

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.

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).

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.

Cerebras' dinner plate-sized wafers provide the space needed to leverage SRAM.

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.

"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.

"Every aspect of the design has been optimized to deliver the highest speeds with massive throughput. With the CS-4, AI is so fast that it fundamentally reshapes product experiences," he added.

In addition to its hardware, Cerebras also hosts its own AI cloud services running on the chips that it rents out to customers.

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.

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.

And while the company offered better-than-anticipated Q3 guidance, it wasn't enough to impress investors on Wall Street.

Email Daniel Howley at dhowley@yahoofinance.com. Follow him on X at @DanielHowley.

Click here for the latest technology news that will impact the stock market**.**

Read the latest financial and business news from Yahoo Finance

── more in #ai-chips 4 stories · sorted by recency
── more on @cerebras systems 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/cerebras-says-latest…] indexed:0 read:2min 2026-08-19 ·