Cactus Compute has released Mirage, a 51.3-million-parameter vision-language model that combines scene description, object detection, optical character recognition, segmentation, spatial analysis and structured decisions in one forward pass. The company reports that the roughly 22 MB model runs locally on a phone’s neural processing unit, or NPU.

The model card lists an Apache 2.0 license and more than 16,000 downloads during Mirage’s first month. Its compact size targets phones, wearables, robots and augmented-reality devices that lack the memory, power or connectivity for multi-gigabyte vision-language models.

Mirage processing images into descriptions, object detections, text, segmentation masks, spatial relations and decisions
Mirage combines several visual-perception tasks in one model invocation.

One pass, six outputs

A single Mirage invocation returns a structured record containing descriptions, detected objects, geometry, recognized text and relationships between elements in an image. Developers can request the following output types: