The package downloads and caches the engine and weights on first use. This repository provides mirage.cact, mirage.safetensors and the model config.
Alternatives to mirage
120 open-weight models that do the same job as mirage, ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning.
33.5B125K ctx Apache 2.0360.8K 510Mar 2025- Same category
- Commercial use OK
Command A+ is an open source model with 25 billion active parameters and 218B total parameters model optimized for agentic, multilingual, and reasoning-heavy tasks with a focus on enterprise performance, while also providing support for vision inputs for processing image inputs.
219BA25.5B200K ctx Apache 2.014.3K 148May 2026- Same category
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
12.2B128K ctx Gemma Terms of Use408.4K 925Mar 2025- Same category
UI-Venus-2 is a general-purpose foundation GUI agent designed to operate across mobile applications, web platforms, and desktop operating systems through a unified closed-loop reasoning–action framework: the agent observes the current interface, reasons about the task state, executes an action, and…
9B256K ctx Unknown licence6.3K 49Aug 2026- Same category
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.
8.5B40K ctx Apache 2.0101.4K 109Aug 2025- Same category
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
236BA22B256K ctx Apache 2.081.5K 421Sept 2025- Same category
- Commercial use OK
Mage-VL is a codec-native, proactive-streaming multimodal foundation model for image and video understanding, whose visual encoder is trained entirely from scratch at a compact 4B scale.
4.7B256K ctx Apache 2.07K 456Jul 2026- Same category
- Commercial use OK
Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy.
9.3BA2Bmoondream-model-license-1.08.7K 103Jun 2026- Same category
Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multilingual, multimodal, fully open, and transparent AI.
72BApache 2.07.2K 149Jul 2026- Same category
- Commercial use OK
We shared the latest progress of the UI-TARS-1.5 model in our blog, which excels in playing games and performing GUI tasks.
8.3B125K ctx Apache 2.0229.7K 624Apr 2025- Same category
- Commercial use OK
Intern-Decision-0.8B is a multimodal structured decision model fine-tuned from Qwen3.5-0.8B. It accepts a shared state, a schema of named questions, and optional images, and returns an answer distribution for every question in one model forward pass.
853M256K ctx Apache 2.04.2K 41Sept 2026- Same category
- Commercial use OK
GLiDE is a decision model from Fastino. Given a state (text or JSON, optionally with images) and one or more typed questions, it returns a probability for every option of every question. Internal use only.
26.1B256K ctx fastino-community3.6K 103Oct 2026- Same category
Inference provider: Fastino — use GLiDE through Fastino's hosted API (POST https://api.fastino.ai/v1/systemone, model fastino/GLiDE). Get an API key · API documentation
26.1B256K ctx fastino-community3.6K 103Oct 2026- Same category
Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.
4.9B36K ctx Apache 2.032.8K 57Dec 2025- Same category
- Commercial use OK
AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflect, and revise.
27.4B256K ctx Apache 2.03.8K 218Sept 2026- Same category
- Commercial use OK
NV-Reason-CT is a 3D vision-language model (VLM) for CT image analysis. It combines a native 3D vision encoder (3D ViT) with a language model and is designed for radiology report generation, general question answering, and multi-step reasoning across chest and abdominal CT volumes.
5.3B256K ctx Custom licence4.3K 96Sept 2026- Same category
- Commercial use OK
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding.
201B256K ctx Apache 2.09.6K 463May 2026- Same category
- Commercial use OK
Groot is a family of open-weight reasoning models for complex real-world tasks. The models are compact and easy to deploy, strong on reasoning and tool-using workloads, and efficient with token budgets.
19.4BA3B256K ctx Apache 2.03.1K 99Oct 2026- Same category
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
27.4B128K ctx Gemma Terms of Use291K 2.1KMar 2025- Same category
This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).
8.3B125K ctx Apache 2.0309.1K 66Feb 2025- Same category
- Commercial use OK
Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification.
12B10M ctx Llama 4 Community License186.7K 141Apr 2025- Same category
Llama Nemotron Nano VL is a leading document intelligence vision language model (VLMs) that enables the ability to query and summarize images from the physical or virtual world.
8.7B128K ctx NVIDIA Open Model License132.5K 188Jun 2025- Same category
- Commercial use OK
LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token.
1.78T512K ctx MIT2.7K 360Nov 2026- Same category
- Commercial use OK
Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.
7.8B64K ctx Apache 2.028.7K 27Dec 2025- Same category
- Commercial use OK