What are the hardware requirements for Mirage?

Mirage requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mirage and how large is it?

Mirage is developed by Cactus-Compute. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Mirage?

Mirage is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mirage by Cactus-Compute — VRAM 0.2GB

Name: Mirage
Author: Cactus-Compute

Mirage is an open-source language model by Cactus-Compute. Features: LLM, VRAM: 0.2GB, License: apache-2.0, LLM Explorer Score: 0.51.

Cactus-compute De Document-question-answering En Es Fr Image-classification Image-segmentation Image-text-to-text Image-to-text It Mirage Nl Object-detection Pl Region:us Visual-question-answering Zero-shot-image-classification Zero-shot-object-detection

Model Card on HF 🤗: https://huggingface.co/Cactus-Compute/mirage

Mirage Parameters and Internals

LLM Name	Mirage
Repository 🤗	https://huggingface.co/Cactus-Compute/mirage
Required VRAM	0.2 GB
Updated	2026-11-09
Maintainer	Cactus-Compute
Model Type	mirage
Model Files	0.2 GB
Supported Languages	en de fr es it nl pl
License	apache-2.0

Rank the Mirage capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation