TinyCorp Breaks Compatibility Barrier: External Nvidia RTX GPUs Now Work with Apple M3 MacBooks for AI Development

AI Developer Gets an External Nvidia RTX GPU Working on a MacBook Pro M3

Don't miss out on our latest stories. Add PCMag as a preferred source on Google. A small AI developer has shown an M3 MacBook Pro using an externally connected Nvidia RTX graphics card for AI calculations. This is not ideal for gaming or even running a display, but it potentially opens the door for AI development on Apple hardware. Since Apple transitioned from Intel processors in its MacBooks to ARM for its own Apple M-series chips, which feature onboard GPUs, compatibility with Nvidia and AMD GPUs has been nonexistent. As TechRadar points out, developers and enthusiasts have attempted to add support to no avail. Now, though, AI developer TinyCorp has shown it's possible. TinyCorp previously developed a method for running an external AMD graphics card on Apple silicon using USB 3, but it has now done the same with Nvidia GPUs on the M-Series MacBooks, leveraging USB 4 and Thunderbolt 4. It hasn't given the full details of how it achieved this, but it showcased an image of it in action. The configuration reportedly works with Nvidia RTX 30, 40, and 50-series GPUs, as well as AMD GPUs like RDNA2, RDNA3, and RDNA4, according to TinyCorp. However, you'll get the best performance from the later models, which feature the latest Tensor Cores and greater quantities of onboard memory. With such a card and the onboard MacBook processing capabilities, developers would be able to run larger language models locally, rather than relying exclusively on cloud deployments of AI, which introduce privacy and latency concerns. For home developers looking to experiment with AI training and model fine-tuning, this is a significant development that could make Apple hardware more relevant in the developer space. As it stands, although Apple's Neural Engine is capable, it's still very limited compared with the power of a discrete GPU, especially Nvidia's high-end RTX 50-series cards, like the RTX 5090. Having access to that kind of power gives a MacBook an enormous amount of additional compute power to handle AI workloads. Still, the process would need to be better understood and the made drivers publicly available if this is going to see any kind of wider adoption. It also currently relies on the TinyCorp-developed TinyGrad framework, which may limit future deployment and development. The proof of concept is impressive and exciting, though, and shows that developers are likely to have a wealth of options for AI development hardware in the future.

Nvidia GPUs quietly find their way into Apple MacBooks

For many years, the idea of 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, has now found a practical path forward after years of failed attempts by others. The company, 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. These standards were designed for high-throughput peripherals like GPU docks, giving developers a cleaner route than the older USB3 interface. 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. Still, there are important limitations. 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. This achievement has direct implications for those working with LLMs and other AI tools that demand high GPU power. By pairing Nvidia's RTX 30, 40, or 50 series GPUs with MacBooks, developers can handle larger datasets or train models locally rather than depending entirely on cloud or data center environments. Such flexibility could make 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.