The world’s fastest GLM-4.6 is now available on Cerebras at 1,000 TPS >>

CS-3 System

For organizations that demand the highest levels of performance, privacy, and control, deploy your very own AI & HPC supercomputer. The revolutionary CS-3 system delivers unmatched speed and efficiency, and easily scales up to 24 trillion parameter models on a single logical device.

Build with us

Cluster-Scale Power
Mini-Fridge Size

At the heart of the CS-3 system is an innovative wafer packaging solution we refer to as the engine block. The engine block delivers power straight into the face of the wafer to achieve the required power density that could not be achieved with traditional packaging. It provides uniform cooling for the wafer via a closed internal water loop. All cooling and power supplies are redundant and hot-swappable so you stay up-and-running at full performance.

Massive Performance,
Minimal Cost.

The CS-3 system is purpose-built for large-scale AI workloads, delivering better performance, lower power consumption, and a smaller footprint compared to GPU-based systems—all at a fraction of the cost.

Seamless Integration

Designed for rapid deployment, the CS-3 installs in days, not weeks or months. It seamlessly connects to existing infrastructure via 12x standard 100 Gigabit Ethernet links, translating standard TCP-IP traffic into Cerebras protocol at full line rate to drive its 900,000 cores.