TinyCorp developed a USB4 adapter enabling Apple MacBooks to run NVIDIA RTX GPUs, expanding GPU compute access to portable devices.

For many years, running Nvidia GPUs on Apple MacBooks was considered unfeasible by both developers and hardware enthusiasts. Apple's decision to move away from Intel processors and fully embrace its ARM-based M-series chips meant the end of official driver support for Nvidia and AMD. These chips rely on a built-in iGPU, removing the need for external GPU compatibility on macOS. Developers and enthusiasts have long attempted to bridge the gap by crafting their own drivers, but success was limited and often unreliable.

TinyCorp, a small AI startup known for building the world's first external AMD GPU to run on Apple Silicon via USB3, has now succeeded in getting Nvidia GPUs to operate on M-series MacBooks through USB4 and Thunderbolt 4 connections. Although TinyCorp has not detailed the full technical process, its success likely depends on using the native PCIe support and higher bandwidth offered by USB4 and Thunderbolt 4, standards designed for high-throughput peripherals like GPU docks. The company's post on X showed a MacBook Pro M3 Max running its open-source Tinygrad framework on an external Nvidia GPU through a USB4 dock, giving developers a cleaner route than the older USB3 interface.

There are important limitations to this solution. The drivers TinyCorp developed are meant specifically for AI workloads rather than gaming or display rendering. Users cannot expect the external GPU to drive a monitor or accelerate macOS graphics. Instead, the focus is on enabling computation-heavy AI tasks, which could be transformative for developers who rely on local resources.

By pairing Nvidia's RTX 30, 40, or 50 series GPUs with MacBooks, developers can now handle larger datasets or train models locally rather than depending entirely on cloud or data center environments. This achievement has direct implications for those working with LLMs and other AI tools that demand high GPU power, potentially making Apple's laptops more relevant in AI research and machine learning experimentation, although this remains a niche use case for now.

TinyCorp's work is impressive, and pairing Apple hardware with Nvidia GPUs in any capacity is an achievement that many thought would never happen. However, its dependence on custom drivers and external docks means that the long-term practicality of this solution remains to be seen.