In a significant shift for its hardware ecosystem, Apple has officially authorized the use of external Graphics Processing Units (eGPUs) on Macs equipped with M-series silicon. This development follows the approval of specialized drivers developed by Tiny Corp, enabling a feature that was previously unsupported or required complex workarounds on Apple’s ARM-based architecture.
The new drivers are engineered to support graphics cards from both AMD and NVIDIA. Connectivity is established through Thunderbolt or USB4 interfaces, which provide the high-bandwidth data transfer necessary for external processing. Consequently, compatibility is limited to Mac models equipped with these specific ports; older or more basic devices with restricted connectivity will not be able to utilize the feature.
If you have a Thunderbolt or USB4 eGPU and a Mac, today is the day you've been waiting for! Apple finally approved our driver for both AMD and NVIDIA. It's so easy to install now a Qwen could do it, then it can run that Qwen… pic.twitter.com/daUsyBHh1W
— the tiny corp (@__tinygrad__) April 1, 2026
Prior to this approval, integrating an eGPU with Apple Silicon was a difficult task for enthusiasts, often involving the deactivation of core system security protocols. The official recognition of these drivers simplifies the installation process, making high-performance graphical expansion more accessible to a broader professional audience. By removing these technical barriers, the integration becomes a more stable and “plug-and-play” experience compared to previous community-driven hacks.
While eGPUs were traditionally marketed toward gamers seeking higher frame rates, the focus of this update is distinctly different. Tiny Corp has designed these drivers with a primary emphasis on Artificial Intelligence (AI) workloads. The goal is to provide additional computational power for:
Running and training Large Language Models (LLMs).
Accelerating complex data processing tasks.
Enhancing machine learning workflows.
Despite this milestone, some functional constraints remain. Notably, there is currently a lack of acceleration for direct video output through the eGPU. However, as hardware demands for AI continue to escalate, this development marks a pivotal step in expanding the utility of M-series Macs for advanced computational research and professional AI development.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。