# Cerebras Unveils CS-4 Rack System, Claims 30x Faster AI Inference Than GPUs

*2026-08-21 02:02 UTC · AI · 1 min read*

> Cerebras launched the CS-4 rack system and WSE-3 Turbo chip, claiming up to 30x faster AI inference than GPU-based servers.

Cerebras Systems launched its CS-4 rack-scale server alongside a new wafer-scale chip, the WSE-3 Turbo, claiming up to 30 times more tokens per second per user than GPU-based systems on large language model inference. First shipments are expected this quarter.

The WSE-3 Turbo packs 4 trillion transistors and 900,000 AI-optimized cores onto a single wafer built on TSMC's 5nm process, doubling its predecessor's compute to 250 PFLOPS and its memory bandwidth to 43.2 petabytes per second, with 44GB of SRAM integrated directly on-chip. The CS-4 rack houses three of these wafers, delivering 750 PFLOPS of total AI compute and 129.6 petabytes per second of memory bandwidth — six times the throughput of a single CS-3 system and ten times higher throughput per watt.

The CS-4 is the first system built on Cerebras' new "Nexus" rack architecture, designed to let the company swap in future wafer generations, including planned CS-5 and CS-6 chips, without redesigning the rack. The launch intensifies competition in AI inference hardware, where Cerebras has positioned wafer-scale chips as a low-latency alternative to Nvidia GPU clusters for serving large models.

## Sources

- [servethehome.com](https://www.servethehome.com/cerebras-intros-faster-wse-3-turbo-processor-and-first-rack-scale-cs-4-system/)
- [nextplatform.com](https://www.nextplatform.com/compute/2026/08/19/cerebras-overclocks-wse-3-waferscale-engine-to-boost-inference-oomph-in-nexus-cs-4/5289400)

---
TechTools News · https://techtools.cz/tools/news/article/2225-cerebras-unveils-cs-4-rack-system-claims-30x-faster-ai-inference-than-gpus
Česká verze: https://techtools.cz/tools/news/clanek/2298-cerebras-predstavil-system-cs-4-tvrdi-ze-je-30x-rychlejsi-v-ai-inferenci-nez-gpu