Nativ: Running AI Models Locally on Mac

Developer Prince Canuma, creator of the MLX-VLM library, released the Nativ app for macOS that allows running AI models locally. The app provides a chat interface and an API server, and also finds already downloaded models from the Hugging Face cache.

Apple

Nvidia aims to occupy every chip in AI data centers

Nvidia is promoting its new Vera Rubin chip system, which combines GPUs and CPUs, positioning itself as a supplier of complete AI systems. The system promises 10x tokens per watt compared to Grace Blackwell and features liquid cooling, cable-free design, and faster installation. Early customers include Microsoft, OpenAI, and Oracle.

NVIDIA Intel Corporation OpenAI