Cerebras CS-3 Inference Cluster (16-node)
A sixteen-node Cerebras inference cluster, provisioned as ten cabinets: eight WSE cabinets holding two CS-3 systems each, plus two NET cabinets. Provisioned heat load is approximately 475 kW, about 440 kW on water and 35 kW on air. That is Cerebras's own provisioned total including networking, not sixteen times the 27 kW system figure. The cluster holds 704 GB of on-chip SRAM and no DRAM. Each engine is rated at 125 petaFLOPS, footnoted by Cerebras as sparse; the sparsity is unstructured, so no dense figure is derived.
We will point you at suppliers who have it. Free, and no signup.
System Details
GPU Configuration
System Specifications
Powered by Cerebras WSE-3
This system utilizes 16 × Cerebras WSE-3 GPUs, each delivering exceptional performance for AI and HPC workloads.
Per GPU TDP
—
Per GPU Memory
—
Process Node
TSMC 5nm
Architecture
Wafer Scale Engine 3
Documentation & Resources
Flopper Spec Sheet
Cerebras CS-3 Inference Cluster (16-node) specifications, generated from our database. Printable.
Vendor product page
Cerebras CS-3 Inference Cluster (16-node) documentation
Cerebras CS-4 datasheet
Cerebras • 2026-08-18
Typical Use Cases
The Cerebras CS-3 Inference Cluster (16-node) runs 16× WSE-3 GPUs over On-wafer fabric per engine, 214 Pb/s; cluster networking via dedicated NET cabinets.