TinyGPU enables external GPUs to run AI models directly on MacsUsers can now leverage AMD and Nvidia cards without bypassing protectionsTinyGPU supports macOS 12.1 and later with Thunderbolt or USB4<\/p>\n
Apple<\/a> Silicon Macs have long been praised for their efficiency and tight hardware-software integration, but they have not been ideal for external GPU<\/a> use.<\/p>\n That changed when Apple officially approved TinyGPU, a driver enabling eGPUs to function as AI accelerators on Apple Silicon machines.<\/p>\n <\/p>\n The approval means that users can now leverage high-performance AMD<\/a> and Nvidia<\/a> cards for AI tasks without needing to bypass system protections like SIP.<\/p>\n Article continues below <\/p>\n You may like<\/p>\n Official Approval Unlocks AI Potential for Mac Users<\/p>\n \u201cIf 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,\u201d TinyCorp said on X<\/a>.<\/p>\n TinyGPU\u2019s functionality focuses exclusively on AI workloads rather than traditional graphics output, allowing complex models to run directly on a Mac Mini or other supported Apple Silicon devices.<\/p>\n The TinyGPU driver supports macOS 12.1 or later, along with devices equipped with USB4 or Thunderbolt 3 and 4 ports.<\/p>\n AMD GPUs from the RDNA3 generation onward and Nvidia cards from the Ampere series are compatible.<\/p>\n Users can run AMD workloads natively, while Nvidia GPUs require a Docker Desktop setup to execute AI computations through NVCC.<\/p>\n Once the driver is installed and approved in the system, even demanding AI models such as Qwen 2.5 27B can run effectively.<\/p>\n TinyGPU\u2019s framework, tinygrad, provides the necessary computational interface, offering a streamlined approach for AI acceleration that had previously been impossible.<\/p>\n What to read next<\/p>\n The timing of this development coincides with the permanent discontinuation of the Mac Pro<\/a>.<\/p>\n Apple has removed the Mac Pro from its website, redirecting the flagship model\u2019s page to the general Mac homepage.<\/p>\n Reports indicate that no new Mac Pro hardware is planned, effectively ending a line that had only seen three updates over the past fourteen years.<\/p>\n Rumors of an M4 Ultra variant never materialized, suggesting limited sales and a perceived lack of demand for high-end desktop configurations.<\/p>\n For many, this shift leaves Apple Silicon Macs without a modular workstation<\/a> alternative \u2014 until now, eGPUs provide a viable route for users who require substantial AI performance.<\/p>\n The combination of TinyGPU with a Mac Mini or other Apple Silicon systems opens new possibilities for professionals and enthusiasts alike.<\/p>\n The ability to connect external GPUs and run AI tools<\/a> directly on macOS introduces a level of flexibility.<\/p>\n As TinyCorp noted, \u201cIt\u2019s so easy to install now a Qwen could do it, then it can run that Qwen,\u201d reflecting the driver\u2019s accessibility and impact.<\/p>\n While Apple has moved away from traditional workstation hardware, eGPU support now lets users turn modest devices into AI-capable systems.<\/p>\n Follow TechRadar on Google News<\/a> and add us as a preferred source<\/a> to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!<\/p>\n And of course you can also follow TechRadar on TikTok<\/a> for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp<\/a> too.<\/p>\n