What is RDMA over Thunderbolt 5, and why does it matter for AI?
RDMA (remote direct memory access) lets one computer read and write another computer’s memory directly, without going through the usual network stack. Apple added RDMA over Thunderbolt 5 in macOS Tahoe 26.2. It cuts latency between Macs enough to make tensor parallelism practical, so a cluster can run a model faster than a single Mac.
It works on Apple silicon Macs with Thunderbolt 5, including every current Mac Studio, Mac mini with an M4 Pro or M5 Pro chip, and MacBook Pro with a Pro or Max chip. Jeff Geerling cites a drop in latency from about 300 microseconds to under 50.
On macOS 26.2 you enable it once per Mac from Recovery mode with the command rdma_ctl enable. Every Mac in an RDMA cluster must be cabled directly to every other one, with Thunderbolt 5 cables, and run the same macOS version.
On a Mac Studio, the Thunderbolt 5 port next to the Ethernet port cannot be used for RDMA.
Sources
Updated