Apple gave me access to this Mac Studio cluster to test RDMA over Thunderbolt, a new feature in macOS 26.2. The easiest way to test it is with Exo 1.0, an open source private AI clustering tool. RDMA lets the Macs all act like they have one giant pool of RAM, which speeds up things like massive AI models.
The stack of Macs I tested, with 1.5 TB of unified memory, costs just shy of $40,000, and if you're wondering, no I cannot justify spending that much money for this. Apple loaned the Mac Studios for testing. I also have to thank DeskPi for sending over the 4-post mini rack containing the cluster.
The last time I remember hearing anything interesting about Apple and HPC (High Performance Computing), was back in the early 2000s, when they still made the Xserve.
They had a proprietary clustering solution called Xgrid... that landed with a thud. A few universities built some clusters, but it never really caught on, and now Xserve is a distant memory.
I'm not sure if its by accident or Apple's playing the long game, but the M3 Ultra Mac Studio hit a sweet spot for running local AI models. And with RDMA support lowering memory access latency from 300μs down to < 50μs, clustering now adds to the performance, especially running huge models.
They also hold their own for creative apps and at least small-scale scientific computing, all while running under 250 watts and almost whisper-quiet.
The two Macs on the bottom have 512 GB of unified memory and 32 CPU cores, and cost $11,699 each. The two on top, with half the RAM, are $8,099 each.
They're not cheap.
But with Nvidia releasing their DGX Spark and AMD with their AI Max+ 395 systems, both of which have a fourth the memory (128 GB maximum), I thought I'd put this cluster through it's paces.
Video
... continue reading