CPU3DAI tools for 3D, video and audio

mirage model for image understanding and extraction appears on HuggingFace

The model Cactus-Compute/mirage with the image-text-to-text task has been published on HuggingFace. The author describes it as a model for image understanding and structured information extraction. The publication date was 05.11.2026.

What it means

The largest weights file — mirage.safetensors — takes up 0.2 GB. The weights are published in safetensors format, and the license is apache-2.0. The model runs through the cactus-compute package, which downloads and caches the engine and weights on first use. There are no quantized builds on the platform yet. The repository contains mirage.cact, mirage.safetensors and the model config. The author also points to the Python API documentation, the list of platforms supported by the runtime, and the source code. The developer gives no details on VRAM or CPU requirements. For those following tools that can be run on your own hardware, this is another openly licensed model with a small footprint — more news in this area can be found in the CPU3D news feed.
Cactus-Compute/mirage — image understanding image-text-to-text · published 05.11.2026 Input image + text mirage model image understanding structure extraction Output structured data mirage.safetensors 0.2 GB · safetensors apache-2.0 license mirage.cact model config in the repository cactus-compute downloads and caches engine and weights Quantization no builds yet Documentation Python API · source code Platforms runtime list More news in the CPU3D news feed
How the method works. The diagram is drawn based on this news note.

See also