ZwZ2-9B is the Qwen3.5-9B-based model in Zooming-without-Zooming-v2 (ZwZ2). It learns to connect visual evidence across regions through comparison, aggregation, matching, and multi-step reasoning. Training uses full images; inference requires no zooming tools.
Alternatives to ZwZ2-9B
120 open-weight models that do the same job as ZwZ2-9B (9.4B vision), 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.
UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation
10.3B64K ctx MIT459 27Nov 2025- Same category
- Similar size (10.3B vs 9.4B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
27.8B256K ctx Apache 2.01.6M 1.1KFeb 2026- Same category
- Larger (27.8B vs 9.4B)
- Commercial use OK
- Widely used
The LLaVA-NeXT model was proposed in LLaVA-NeXT: Improved reasoning, OCR, and world knowledge by Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, Yong Jae Lee.
7.6BApache 2.0146K 315Feb 2024- Same category
- Similar size (7.6B vs 9.4B)
- Commercial use OK
In this report, we share our efforts to build a compact yet powerful VLM, MiMo-VL-7B. MiMo-VL-7B comprises (1) a native resolution ViT encoder that preserves fine-grained visual details, (2) an MLP projector for efficient cross-modal alignment, and (3) our MiMo-7B language model, specifically…
8.3B125K ctx MIT1.8K 171May 2025- Same category
- Similar size (8.3B vs 9.4B)
- Commercial use OK
Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses
4.7B256K ctx Apache 2.05.7K 233Oct 2026- Same category
- Similar size (4.7B vs 9.4B)
- Commercial use OK
- Newer release
This repository contains models presented in the paper Qianfan-OCR: A Unified End-to-End Model for Document Intelligence.
8.8B32K ctx Custom licence371 42Sept 2025- Same category
- Similar size (8.8B vs 9.4B)
The LLaVA-OneVision models are 0.5/7/72B parameter models trained on LLaVA-OneVision, based on Qwen2 language model with a context window of 32K tokens.
8B32K ctx Apache 2.027.3K 65Jun 2024- Same category
- Similar size (8B vs 9.4B)
- Commercial use OK
TODO - [X] Release model weights. - [X] Release the inference code w/o. efficiency optimization. - [X] Release the inference code w. chunk-based prefill. - [ ] Release the inference code w. chunk-based prefill & bi-level kvs decoding.
8.1B32K ctx Apache 2.01.7K 58May 2025- Same category
- Similar size (8.1B vs 9.4B)
- Commercial use OK
NuMarkdown-8B-Thinking is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file.
8.3B125K ctx MIT901 500Jul 2025- Same category
- Similar size (8.3B vs 9.4B)
- Commercial use OK
MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.
11.3B256K ctx Apache 2.0103 19Jul 2026- Same category
- Similar size (11.3B vs 9.4B)
- Commercial use OK
A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
8.1B32K ctx Unknown licence16.4K 1.1KAug 2024- Same category
- Similar size (8.1B vs 9.4B)
MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.
11.3B256K ctx Apache 2.0195 108Apr 2026- Same category
- Similar size (11.3B vs 9.4B)
- Commercial use OK
Please note that in our Demo, ARC-Hunyuan-Video-7B is the model consistent with the model checkpoint and the one described in the paper, while ARC-Hunyuan-Video-7B-V0 only supports video description and summarization in Chinese.
8.6B1K ctx Unknown licence579 40Jul 2025- Same category
- Similar size (8.6B vs 9.4B)
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 Use1M 1.7KFeb 2025- Same category
- Smaller (4.3B vs 9.4B)
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 2.032.7K 57Dec 2025- Same category
- Similar size (4.9B vs 9.4B)
- Commercial use OK
UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities.
8.3B32K ctx Apache 2.02.9K 236Jan 2025- Same category
- Similar size (8.3B vs 9.4B)
- Commercial use OK
This section describes the MedGemma model and how to use it.
4.3B128K ctx health-ai-developer-foundations470.4K 1.2KMay 2025- Same category
- Smaller (4.3B vs 9.4B)
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 2.072.1K 114Apr 2026- Same category
- Smaller (4B vs 9.4B)
- Commercial use OK
The LLaVA-Video models are 7/72B parameter models trained on LLaVA-Video-178K and LLaVA-OneVision Dataset, based on Qwen2 language model with a context window of 32K tokens.
8B32K ctx Apache 2.012.1K 127Sept 2024- Same category
- Similar size (8B vs 9.4B)
- 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 2.06.9K 456Jul 2026- Same category
- Similar size (4.7B vs 9.4B)
- Commercial use OK
Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source.
8B4K ctx Apache 2.09.1K 568Sept 2024- Same category
- Similar size (8B vs 9.4B)
- 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
- Smaller (4.5B vs 9.4B)
- Commercial use OK
The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out).
10.6B128K ctx Llama 3.2 Community License7K 620Sept 2024- Same category
- Similar size (10.6B vs 9.4B)
In this report, we share our efforts to build a compact yet powerful VLM, MiMo-VL-7B. MiMo-VL-7B comprises (1) a native resolution ViT encoder that preserves fine-grained visual details, (2) an MLP projector for efficient cross-modal alignment, and (3) our MiMo-7B language model, specifically…
8.3B125K ctx MIT992 57May 2025- Same category
- Similar size (8.3B vs 9.4B)
- Commercial use OK