- TinyGPU allows external GPUs to run AI models directly on Mac
- Users can now take advantage of AMD and Nvidia cards without bypassing protections
- TinyGPU is compatible with macOS 12.1 and later with Thunderbolt or USB4
Apple Silicon Macs have long been praised for their efficiency and tight integration of hardware and software, but they have not been ideal for the use of external GPUs.
That changed when Apple officially approved TinyGPU, a controller that allows eGPUs to function as artificial intelligence accelerators in Apple Silicon machines.
The approval means that users can now take advantage of high-performance AMD and Nvidia cards for AI tasks without needing to bypass system protections like SIP.
Article continues below.
Official approval unlocks the potential of AI for Mac users
“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,” TinyCorp said on X.
TinyGPU functionality focuses exclusively on AI workloads rather than traditional graphics output, allowing complex models to run directly on a Mac Mini or other compatible Apple Silicon devices.
The TinyGPU controller is compatible with macOS 12.1 or later, along with devices equipped with USB4 or Thunderbolt 3 and 4 ports.
AMD GPUs from the RDNA3 generation onwards and Nvidia Ampere series cards are supported.
Users can run AMD workloads natively, while Nvidia GPUs require a Docker Desktop setup to run AI calculations via NVCC.
Once the driver is installed and approved on the system, even the most demanding AI models, such as the Qwen 2.5 27B, can work effectively.
TinyGPU’s framework, tinygrad, provides the necessary computational interface and offers a simplified approach to AI acceleration that has previously been impossible.
The timing of this development coincides with the permanent discontinuation of the Mac Pro.
Apple has removed the Mac Pro from its website, redirecting the flagship model’s page to the general Mac home page.
Reports indicate that no new Mac Pro hardware is planned, effectively ending a line that had only received three updates in the last fourteen years.
Rumors about an M4 Ultra variant never materialized, suggesting limited sales and an apparent lack of demand for high-end desktop configurations.
For many, this change leaves Apple Silicon Macs without a modular workstation alternative; So far, eGPUs provide a viable route for users requiring substantial AI performance.
Combining TinyGPU with a Mac Mini or other Apple Silicon systems opens up new possibilities for professionals and enthusiasts alike.
The ability to connect external GPUs and run AI tools directly on macOS introduces a level of flexibility.
As TinyCorp noted, “It’s so easy to install that now a Qwen could do it and then you can run that Qwen,” reflecting the accessibility and impact of the driver.
While Apple has moved away from traditional workstation hardware, eGPU support now allows users to turn modest devices into AI-enabled systems.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
