Apple Demos Running 1-Trillion-Parameter Kimi K2.6 Model on 4 Mac Studios at WWDC26
English summary
On June 18, Apple's developer channel posted an 88-minute WWDC26 special session video recorded at Steve Jobs Theater. The closing segment demonstrates local inference of the 1-trillion-parameter Kimi K2.6 model across four Mac Studios using LM Studio. This setup leverages RDMA over Thunderbolt, a new macOS Tahoe 26.2 feature that provides microsecond-latency direct memory access between machines. Kimi K2.6, released by Chinese startup Moonshot AI in April 2026, features enhanced coding, long-horizon task execution, and agentic clustering. The video also shows an AI app builder creating a WWDC badge tracker with 3D animation and Visual Intelligence from a single prompt.
Chinese summary
2026年6月18日，苹果开发者账号发布了WWDC26特别讲座全程视频。末尾环节演示了在四台Mac Studio上通过LM Studio本地运行1万亿参数的Kimi K2.6模型。其关键是将macOS Tahoe 26.2中引入的RDMA over Thunderbolt技术用于模型推理，该技术可实现微秒级延迟的机器间直接内存访问。Kimi K2.6由中国初创公司月之暗面于2026年4月发布，大幅升级了代码编写、长程任务执行和Agent集群能力。视频还展示了仅凭单条提示词生成具备3D动画与视觉智能功能的WWDC徽章追踪应用。
Key points
Apple demoed local inference of the 1-trillion-parameter Kimi K2.6 LLM across four Mac Studios using LM Studio.
苹果演示了在四台Mac Studio上通过LM Studio本地运行1万亿参数的Kimi K2.6大语言模型。
The setup used RDMA over Thunderbolt, a new macOS Tahoe 26.2 feature providing microsecond-latency direct memory access between Macs.
配置利用了macOS Tahoe 26.2新引入的RDMA over Thunderbolt技术，实现Mac间的微秒级直接内存访问。
Kimi K2.6 was released by Moonshot AI in April 2026 with improvements in code generation, long-task execution, and agentic clustering.
Kimi K2.6由月之暗面于2026年4月发布，在代码生成、长程任务执行和Agent集群能力上有显著提升。
The same video showed an AI app builder that created a complex WWDC badge tracker app with 3D animations from a single prompt.
同场视频展示了一款AI应用构建器，通过单条提示词生成了带3D动画的复杂WWDC徽章追踪应用。