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.
VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.
10B256K ctx Apache 2.073.4K 42Jul 2026- Same category
- Commercial use OK
LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.
3.1B32K ctx lfm1.054.2K 239Aug 2026- Same category
MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity.
9.4B256K ctx MIT38.9K 715Sept 2026- Same category
- Commercial use OK
FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt.
9.4B256K ctx Apache 2.031K 83Oct 2026- Same category
- Commercial use OK
LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.
1.9B125K ctx lfm1.030.7K 288Oct 2026- Same category
Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.
9.4B256K ctx Apache 2.032.7K 934Sept 2026- Same category
- Commercial use OK
H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts).
4.5B256K ctx Apache 2.026.1K 109Oct 2026- Same category
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
31.1BA3B256K ctx Apache 2.0399.2K 629Sept 2025- Same category
- Commercial use OK
We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.
305BA15.2B1M ctx MIT28.6K 971Aug 2026- Same category
- Commercial use OK
* License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use. MedGemma has not been evaluated or optimized for multi-turn applications.
4.3B128K ctx health-ai-developer-foundations183.5K 1.2KJan 2026- Same category
WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…
2.4B256K ctx Apache 2.018.5K 89Oct 2026- Same category
- Commercial use OK
Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix.
631M16K ctx Custom licence26.5K 174Sept 2026- Same category
- Commercial use OK
d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens.
1.9B125K ctx lfm1.017.1K 352Oct 2026- Same category
Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…
1TA52B1M ctx Custom licence20.6K 1.7KSept 2026- Same category
Model Summary: Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight…
4B128K ctx Apache 2.067.8K 115Apr 2026- Same category
- Commercial use OK
d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.
3.1B32K ctx lfm1.019.1K 512Oct 2026- Same category
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.
3.8B125K ctx Qwen Research License1.9M 755Jan 2025- Same category
- Widely used
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
236BA22B256K ctx Apache 2.0317.9K 430Sept 2025- Same category
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
33.4B256K ctx Apache 2.0215.6K 261Oct 2025- Same category
- Commercial use OK
👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.
321BA18.3B1M ctx MIT20.1K 87Aug 2026- 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.
26.5BA4B256K ctx Apache 2.062.3K 479Mar 2026- Same category
- Commercial use OK
North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation for prototyping, task-specific fine-tuning, and specialized multimodal applications.
2.5B500K ctx Apache 2.016.7K 155Aug 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.
4.3B128K ctx Gemma Terms of Use1.1M 1.7KFeb 2025- Same category
Authors: Meta Superintelligence Labs Model Release Date: October 2026 License: Muse Model License
822BA42B1M ctx muse-model-license12.9K 765Sept 2026- Same category