Apple is developing an M7 Ultra chip with unified memory that could reach 1.5TB, according to Techub, citing Bloomberg reporter Mark Gurman. The chip is expected to arrive in 2028, with performance targets said to be close to Nvidia’s Blackwell-class accelerators. The report says the design would use a unified memory architecture, which can remove data-transfer bottlenecks between the CPU and GPU and make the chip suitable for local inference of large language models. If Apple’s silicon becomes competitive with Nvidia in AI workloads, it could give decentralized computing networks another hardware option and affect equipment choices in crypto mining and on-chain inference markets.
Apple is developing an M7 Ultra chip whose unified memory could reach 1.5TB, according to Techub, citing Bloomberg reporter Mark Gurman. The chip is expected to launch in 2028, with performance targets close to Nvidia’s Blackwell-class accelerators.
The report says the M7 Ultra would use a unified memory architecture. That design can remove data-transfer bottlenecks between the CPU and GPU, making the chip suitable for local inference of large language models.
If Apple’s chips become competitive with Nvidia in AI performance, they could offer an alternative hardware option for decentralized computing networks and influence hardware selection in crypto mining and on-chain inference markets.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
