South Korean startup DeepX Co. plans to spend more than $100 million developing a next-generation artificial intelligence chip using Samsung Electronics Co.’s advanced 2 nanometer manufacturing process.
DeepX has finished the design of the DX-M2 and sent the final plans to Samsung’s foundry unit for production, according to a statement from DeepX. The company expects to secure its first silicon by March 2027, before moving toward customer evaluations and mass manufacturing in 2028.
The project is expected to cost more than $100 million, including performance verification costs and production engineering expenses.
DeepX is targeting robots, industrial equipment and AI-enabled personal computers for the DX-M2. The chip is designed to run generative-AI models using about 5 watts of power, according to the company.
The investment is a significant bet by DeepX on running AI models directly on devices rather than relying on computing power in remote data centers. The approach can reduce energy use, costs and delays associated with sending data back and forth to the cloud.
DeepX’s semiconductors are intended for AI work and applications outside of data centers, which are facing mounting backlash over their massive power and water consumption. (Bloomberg)
