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.
LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.
449M125K ctx lfm1.043.1K 240Apr 2026- Same category
The main purpose of text image correction is to carry out geometric transformation on the image to correct the document distortion, inclination, perspective deformation and other problems in the image, so that the subsequent text recognition can be more accurate.
?BApache 2.0454.3K 14Jun 2025- Same category
- Commercial use OK
This section describes the MedGemma model and how to use it.
4.3B128K ctx health-ai-developer-foundations468.6K 1.2KMay 2025- Same category
NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding.
957M9K ctx NVIDIA Open Model License112K 174Nov 2025- Same category
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
32.7B256K ctx Apache 2.043.8K 609Mar 2026- Same category
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.0134.9K 235Oct 2025- Same category
- Commercial use OK
NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.
74.9BA9B256K ctx openmdw-1.18.7K 58Oct 2026- Same category
- Commercial use OK
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
1.3B256K ctx Apache 2.026.6K 34May 2026- Same category
- Commercial use OK
The Document Image Orientation Classification Module is primarily designed to distinguish the orientation of document images and correct them through post-processing.
?BApache 2.0330.5K 24Jun 2025- Same category
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
36BA3B256K ctx Apache 2.042K 160Feb 2026- Same category
- Commercial use OK
Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses
4.7B256K ctx Apache 2.05.5K 231Oct 2026- Same category
- Commercial use OK
NVIDIA Cosmos Reason 2 is an open, customizable, 8B-parameter reasoning vision language model (VLM) for physical AI and robotics that enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.
8.8B256K ctx NVIDIA Open Model License60.2K 265Dec 2025- Same category
- Commercial use OK
SenseNova-Loop-9B-Preview is a multimodal language model developed for long-context and agentic workflows. It accepts text and images and generates text for applications that combine document understanding, coding, and interaction with external tools.
9.7B256K ctx Apache 2.05.5K 322Oct 2026- Same category
- Commercial use OK
We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through…
125BA5.9B128K ctx MIT7.3K 128Sept 2026- Same category
- Commercial use OK
We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.
34.4B256K ctx exaone23.4K 193Apr 2026- Same category
LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI.
3.8B32K ctx nvidia-license31.8K 3.2KMar 2026- Same category
One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.
27.8BApache 2.08.3K 542Aug 2026- Same category
- Commercial use OK
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
10.3B128K ctx MIT59.8K 634Dec 2025- 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.
8.7B36K ctx Apache 2.050.6K 201Dec 2025- Same category
- Commercial use OK
Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. 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.
4.5B256K ctx Apache 2.05.9K 96Sept 2026- Same category
- Commercial use OK
Qwen-Drive-1.0 retains the architecture of the pretrained Qwen3.5 vision-language model and integrates 3D perception, visual question answering, and motion planning within a unified framework.
4.5BApache 2.07.3K 259Aug 2026- Same category
- Commercial use OK
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.
8.9BApache 2.09.4K 189Jul 2026- Same category
- Commercial use OK
Flora-rewarder-27B produces outcome rewards (an episode-level success score), used for monitoring real-world deployments, and process rewards (dense action-quality scores over short time steps), used during reinforcement learning-based post-training.
27.8B256K ctx NVIDIA Non-Commercial License5.5K 23Oct 2026- Same category
Flora-captioner-27B generates one action instruction for a supplied target interval in a robot or human manipulation video. It uses neighboring video context to disambiguate the intended local operation.
27.4B256K ctx NVIDIA Non-Commercial License5.6K 44Oct 2026- Same category