Apple (AAPL) is giving investors another reason to reassess its artificial intelligence (AI) strategy as the company reportedly explores building its own enterprise AI servers. According to The Information, Apple is developing a server designed around its future M8 Ultra chips, with NVIDIA's (NVDA) NVLink Fusion technology potentially used to connect the processors. The project could mark Apple’s return to the enterprise server market after discontinuing its Xserve line in 2011.
The reported move would represent a significant expansion of Apple’s in-house silicon strategy beyond iPhones, Macs, and other consumer devices. Unlike AI systems focused primarily on training large models, the proposed servers are reportedly intended for AI inference workloads, potentially supporting developers, businesses, and government customers. However, the project remains in the development stage, is not expected to reach the market until 2029, and could still be changed or canceled.