Developer Prince Canuma, creator of the MLX-VLM library, released the Nativ app for macOS, which allows running AI models locally. The app provides a chat interface and API server, and also finds already downloaded models from Hugging Face cache.
Apple
A journalist combined four Mac Studio units with M3 Ultra into a cluster with a total memory of 1.5 TB using RDMA technology via Thunderbolt 5. The cluster ran massive AI models such as Kimi K2 Thinking (over 600 GB), which cannot be loaded on a single computer. The project was implemented using the open-source tool Exo 1.0.
Apple
NVIDIA
Exo
Moonshot AI
DeepSeek
Alibaba/Qwen