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.