Etched raises $120M to build Sohu – Learn more
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Careers
Blog
A front side render of the Sohu by Etched transformer against a black background

Meet Sohu: the world's first transformer ASIC

_Transformers etched into silicon

By burning the transformer architecture into our chips, we can run AI models an order of magnitude faster and cheaper than GPUs.

Llama 70B throughput
NVIDIA
8xH100
NVIDIA
8xB200
> 500,000
tokens/sec
Etched
8xSohu
A front-side 3D render of the Sohu by Etched

_Build products that are impossible with GPUs

Real-time voice agents

Ingest thousands of words in milliseconds

Better coding with tree search

Compare hundreds of responses in parallel

Multicast speculative decoding

Generate new content in real-time

_Run tomorrow's trillion parameter models

Only one core
Fully open-source software stack
Expansible to 100T param models
Beam search and MCTS decoding
144 GB HBM3E per chip
MoE and transformer variants
An angled 3D render of Sohu by Etched