[{"data":1,"prerenderedAt":30},["ShallowReactive",2],{"nr-en-cerebras-cs4-doppelte-leistung-chip":3},{"slug":4,"title":5,"dek":6,"date":7,"time":8,"publishedAt":9,"updated":10,"updatedAt":10,"dateFmt":11,"updatedFmt":10,"kind":12,"tier":13,"author":14,"authorName":15,"topics":16,"tracker":22,"trackerLabel":23,"headlineStat":24,"image":25,"ogImage":26,"imageAlt":5,"csv":10,"minutes":27,"words":28,"html":29},"cerebras-cs4-doppelte-leistung-chip","Cerebras CS-4: Double Performance on Same Chip","AI accelerator maker Cerebras has unveiled its new CS-4, claiming it's the fastest inference system on the market. The trick: same 5nm chip, but significantly higher clock speed.","2026-08-24","12:28","2026-08-24T12:28:00+02:00","","August 24, 2026","news","standard","ideal-syka","Ideal Syka",[17,18,19,20,21],"AI Hardware","Inference","Accelerator","Data Center","Performance","\u002Fstand-der-ki","AI Hardware Progress","4,400 tokens per second","\u002Fnewsroom\u002Fimg\u002Fcerebras-cs4-doppelte-leistung-chip.webp","\u002Fog-nr\u002Fcerebras-cs4-doppelte-leistung-chip.en.png",2,372,"\u003Cp>Cerebras has unveiled its new AI accelerator CS-4. According to CEO Andrew Feldman, it's the fastest system in the industry. The system doubles the performance of its predecessor CS-3, even though the underlying chip remains identical – Cerebras increases the clock rate through more power and better cooling.\u003C\u002Fp>\n\u003Ch2>The essentials\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>The CS-4 is a \u003Cstrong>rack-scale solution\u003C\u002Fstrong>: A complete server cabinet with compute units, power, and cooling technology for data centers\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Performance doubled\u003C\u002Fstrong>: Up to \u003Cstrong>4,400 tokens per second\u003C\u002Fstrong> per user – according to Cerebras, up to \u003Cstrong>30 times faster\u003C\u002Fstrong> than Nvidia GPU solutions\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Three instead of two wafers\u003C\u002Fstrong> per rack; the 5nm chip \u003Cstrong>WSE-3\u003C\u002Fstrong> remains unchanged\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Memory constant\u003C\u002Fstrong>: 44 GB per wafer, same as the predecessor\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Modular design for faster deployment\u003C\u002Fh2>\n\u003Cp>Cerebras is introducing a new "backpack" design with the CS-4 to accelerate setup. At the same time, the company is pursuing \u003Cstrong>disaggregated inference\u003C\u002Fstrong> – collaborating with other vendors like AMD and AWS Trainium. This means: Not everything needs to run on Cerebras hardware; components can be modularly combined with other systems.\u003C\u002Fp>\n\u003Cp>Memory capacity per wafer remains at 44 GB – no improvement here. This is a point that SemiAnalysis analysts view critically: progress on the networking side appears rather limited.\u003C\u002Fp>\n\u003Ch2>Who's already using it?\u003C\u002Fh2>\n\u003Cp>Cerebras hardware is already in use. OpenAI, for instance, uses the systems for Codex Spark. This shows: The hardware isn't just an announcement but is already being deployed productively by established AI providers.\u003C\u002Fp>\n\u003Cp>Further technical details on the CS-4 are expected at the Hot Chips conference.\u003C\u002Fp>\n\u003Ch2>What this means for you\u003C\u002Fh2>\n\u003Cp>For infrastructure decision-makers in German mid-market companies, the CS-4 is interesting if you need high-performance AI inference – that is, fast processing of requests in production systems. The promised 30-fold speed advantage over GPU solutions could be relevant at high throughput. However, keep in mind: Cerebras specializes in inference, not training. And the market remains dominated by Nvidia – whether an alternative solution is worth the effort depends on your specific requirements. But the announcement shows: there's movement in the market beyond the big GPU players.\u003C\u002Fp>\n\u003Ch2>Sources\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fthe-decoder.de\u002Fcerebras-stellt-cs-4-vor-doppelte-leistung-gleicher-chip\u002F\">The Decoder (DE)\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cem>Editorially owned by \u003Ca href=\"\u002Fen\u002Fautor\u002Fideal-syka\">Ideal Syka\u003C\u002Fa>. Sources and method: \u003Ca href=\"\u002Fen\u002Fredaktion\">Newsroom & method\u003C\u002Fa>. Tips and corrections: \u003Ca href=\"mailto:ai@i6eal.de\">ai@i6eal.de\u003C\u002Fa>.\u003C\u002Fem>\u003C\u002Fp>\n",1787567467774]