A 45-million-parameter model that fits in a 14MB binary
Cactus Compute's open model Needle 2 is built for tool calling. It ships as a single 14MB binary and runs a full session in about 28MB of RAM.
Models
Cactus Compute's open model Needle 2 is built for tool calling. It ships as a single 14MB binary and runs a full session in about 28MB of RAM.
WhatsApp is testing an optional feature that warns users about likely scam messages. The model runs entirely on the device, and no message content leaves it for classification.