Apple · Chips and hardware · Models
Apple ran a 1 trillion parameter model on four Mac Studios fed from one outlet
This story was corrected after publication (Oct. 9, 2026). Details
In the demonstration four machines worked together on a coding task while drawing power from a single wall socket. The Mac Studio with the M5 Ultra chip supports up to 512GB of unified memory. The machines in the demonstration had 256GB each; linking four gives roughly 1TB of shared memory, enough to run a trillion-parameter model. The machines are joined into a low-latency cluster using RDMA over Thunderbolt. It means work normally associated with data-center infrastructure can sit on a desk.
Sources
- INSIDE, “四台 Mac Studio、一般家用插座：Apple 展示如何在桌上跑兆級 AI 模型”, (inside.com.tw)
- Apple, “Apple introduces new Mac Studio with M5 Max and M5 Ultra”, (apple.com)
Corrections and updates
- The version first posted on Instagram implied the machines in the demonstration had 512GB each, which would add up to 2TB, not 1TB. According to INSIDE, each machine had 256GB; the text has been corrected.
About this story
This story was posted on Instagram by @jarrus.tech on Sept. 27, 2026.
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/apple-mac-studio-cluster
This story in Turkish: Apple, 1 trilyon parametreli bir modeli tek prizden beslenen dört Mac Studio’da çalıştırdı
On the same topic
AWS adds Chinese lab Z.ai’s GLM 5.3 model to Amazon Bedrock
AWS added GLM 5.3, a 753-billion-parameter model from Beijing-based Z.ai (formerly Zhipu AI), to Amazon Bedrock for eligible enterprise customers on October 5.
Nvidia unveils a 64 GB DGX Spark that runs models of up to 100 billion parameters locally
Nvidia announced a 64 GB configuration of its DGX Spark desktop AI computer on October 2, sold through partners from October 23 at a starting price of $4,999.
Microsoft releases three new voice models, one transcribing 60 languages in real time
On October 1, Microsoft AI announced MAI-Transcribe-2-Streaming, which transcribes 60 languages in real time, and the 23-language MAI-Voice-2.1 and Flash.