Project
Cerebras's first multi-wafer rack system, combining three refreshed WSE-3 Turbo wafers with integrated power delivery, scale-up networking and liquid cooling.
Gimlet Labs plans 100 MW of Cerebras-powered inference capacity, pairing wafer-scale chips with GPUs for different phases of each request. For buyers, the quoted 3,000 tokens per second is a company target until measured results appear.
Reality
More memory on a Cerebras wafer arrives with CS-6, two generations out. Everything shipping before then, Nexus included, is rack engineering around the SRAM budget the wafer already has, and long contexts are where that budget hurts.
Reality
The Nexus rack, not the WSE-3, is now the thing Cerebras ships. That makes upgrade cadence the number buyers should price, and 10,000 tokens per second a target rather than a plan input.
Reality
The Cambridge company says routing agentic work across Nvidia, AMD and Google chips doubles accuracy at a quarter of the cost. No customer has confirmed those numbers.
Reality
The first multi-wafer Cerebras system pairs a doubled clock with rebuilt power delivery and interconnect. The compute claims rest on WSE-3 Turbo dies that are otherwise unchanged.
Reality