About Etched
Etched designs Sohu, a chip built only for transformer models, the neural network type behind most large language models. A GPU is flexible and carries circuitry for many kinds of workloads. By fixing the design around the transformer, Etched aims to spend more of the chip on useful arithmetic, at the cost of being unable to run many other model types. Etched was founded in 2022 by Gavin Uberti, Chris Zhu and Robert Wachen, and the company says Sohu is made on TSMC 4nm.
Etched was founded in 2022 and is based in San Francisco, CA, United States. It is listed under ASICs, AI Accelerators. Reported funding is $500M round at $5B valuation (Jan 2026, Stripes-led; total ~$1B).
Compute Technologies
- ASICs
- AI Accelerators
What Etched works on
ASICs
An ASIC, or application-specific integrated circuit, is a chip designed to do one job or a narrow set of jobs. Its circuits are fixed when the chip is made. A CPU can run any program; an ASIC does what it was designed for and nothing else.
AI Accelerators
An AI accelerator is a chip, or a part of a chip, designed to run machine learning faster or with less energy than a general-purpose processor. The category includes GPUs, TPUs, neural processing units (NPUs) and chips from many startups.
Also in United States
deepsilicon, Ouster, Cadence Design Systems, Uhnder, Empower Semiconductor
