Apple

CLaRa-7B-Instruct

CLaRa-7B-Instruct is an instruction-tuned unified Retrieval-Augmented Generation (RAG) model developed by Apple. It integrates semantic document compression at 16× and 128× ratios, enabling efficient instruction-following question answering directly from compressed document representations.

Container

Container is an open-source tool developed by Apple for creating and running Linux containers as lightweight virtual machines on macOS. Written in Swift and optimized for Apple Silicon, it leverages the Virtualization.framework to provide a native and efficient containerization experience on Mac devices.

LensVLM

LensVLM-9B is a 9B-parameter vision-language model designed to process compressed images of text by selectively expanding relevant regions to their uncompressed form. By utilizing a learned tool-based approach, it maintains high accuracy in document and code understanding tasks while significantly reducing the visual token count required for processing.

python-apple-fm-sdk

The python-apple-fm-sdk is a Python library developed by Apple that provides bindings to access the on-device model at the core of Apple Intelligence through the Foundation Models framework. This SDK enables developers to integrate advanced machine learning capabilities into their applications by leveraging Apple's proprietary models.