# Cactus Compute's Mirage brings vision tasks on-device

> The new open vision-language model targets detection, segmentation, and visual Q&A without relying on the cloud.

Published by The Open Weights on Nov 5, 2026. Canonical: https://theopenweights.com/news/mirage-z2ui

## Key facts

- Company: Cactus Compute
- Model: Mirage
- Version: mirage
- Category: Vision-Language
- Modalities: Vision-Language
- License: Other (Open weights, commercial use allowed)
- Architecture: mirage
- Significance: minor
- Published: 2026-11-05
- Last verified: 2026-11-20
- Hugging Face: https://huggingface.co/Cactus-Compute/mirage
- Canonical URL: https://theopenweights.com/news/mirage-z2ui

Cactus Compute has released [Mirage](https://huggingface.co/Cactus-Compute/mirage), a vision-language model designed to run directly on-device. Rather than routing images through a remote API, Mirage is built to handle visual understanding locally, spanning detection, segmentation, and visual question answering within a single model.

That combination is notable. Many compact vision models specialize in one task, but Mirage positions itself as a more general-purpose tool that can both localize objects and answer open-ended questions about what it sees. For developers building camera-driven apps, that flexibility can reduce the number of separate models an application needs to ship.

## Why it matters

On-device inference has become one of the clearer trends in open-weights AI, driven by concerns about latency, cost, and privacy. Keeping vision workloads local means images never have to leave the device, which is appealing for consumer apps, robotics, and anything operating with intermittent connectivity.

- Runs on-device, avoiding cloud round-trips
- Supports detection, segmentation, and VQA in one model
- Released on Hugging Face under a custom license

Cactus Compute has not published detailed parameter counts, context length, or benchmark figures alongside this initial release, so independent evaluation will determine how Mirage holds up against established small vision-language models. The weights and documentation are available now on [Hugging Face](https://huggingface.co/Cactus-Compute/mirage).

## Get the model

- [Hugging Face](https://huggingface.co/Cactus-Compute/mirage)

## Sources

- [Cactus-Compute/mirage](https://huggingface.co/Cactus-Compute/mirage) — Hugging Face, Nov 5, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Cactus Compute's Mirage brings vision tasks on-device", The Open Weights, Nov 5, 2026, https://theopenweights.com/news/mirage-z2ui