Tiny ~51M-parameter vision model from Cactus Compute for on-device object detection, text reading and spatial understanding.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Mirage is a small vision model from Cactus Compute, a company focused on running AI models on phones and other edge devices. According to a creator summary, it has about 51 million parameters and occupies roughly 22 MB when quantized to 2 bits.
It is reported to detect objects, read text in images and understand spatial relations between objects. Reported inference time is around 0.1 seconds on a phone, which targets fully local, on-device use without a cloud round trip.
The model and code are reported as released publicly. The official pages could not be fetched, so the license, exact release date, download locations and benchmark results are unverified here.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Tiny ~51M-parameter vision model (22 MB with 2-bit quantization) that detects objects, reads text and understands spatial relations, running in ~0.1 s on a phone. Model and code released.
Closest neighbours by meaning, not just by category.
Model · Cactus Compute
Tiny 29M–121M parameter on-device model for tool calling and extraction, shipped as an 8–29 MB binary.
Model · Cactus
Tiny on-device tool-calling and extraction model from Cactus, shipped as an 8–29 MB binary for phones, wearables and microcontrollers.
Model · Cactus
Compact 16.9 MB speech-to-text model from Cactus that runs on CPU with no dependencies.
Model · Mirage
Avatar video model from Mirage, marketed for identity preservation in AI-generated talking-person videos.
Model · Nvidia
Nvidia vision-language model for object detection and visual grounding that decodes whole bounding boxes in parallel.
Library
Open-source streaming MoE inference framework for running large sparse models on laptops, phones and single-GPU PCs.
