WeMM-Video-2B is the dense 2B checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.
Alternatives to WeMM-Video-2B
120 open-weight models that do the same job as WeMM-Video-2B (3.3B 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.
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 2.06.7K 259Aug 2026- Same category
- Similar size (4.5B vs 3.3B)
- 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 lfm1.029.8K 297Oct 2026- Same category
- Similar size (1.9B vs 3.3B)
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 3.3B)
- 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.
4.3BGemma Terms of Use175.8K 180Feb 2025- Same category
- Similar size (4.3B vs 3.3B)
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 lfm1.016.8K 335Oct 2026- Same category
- Similar size (1.9B vs 3.3B)
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.
3.4BA1.2B4K ctx DeepSeek License28K 273Dec 2024- Same category
- Similar size (3.4B vs 3.3B)
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 3.3B)
- Commercial use OK
A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
4.1B32K ctx Apache 2.030.1K 465Jul 2025- Same category
- Similar size (4.1B vs 3.3B)
- Commercial use OK
S5-nano is a 4B-parameter model from Maritaca AI. It has two modes:
4.7B256K ctx Apache 2.02.3K 83Nov 2026- Same category
- Similar size (4.7B vs 3.3B)
- Commercial use OK
Model Summary: Granite-4.0-3B-Vision is a vision-language model (VLM) designed for enterprise-grade document data extraction. It focuses on specialized, complex extraction tasks that ultracompact models often struggle with:
4B128K ctx Apache 2.03.3K 113Mar 2026- Same category
- Similar size (4B vs 3.3B)
- Commercial use OK
LFM2-VL-3B is the newest and most capable model in Liquid AI's multimodal LFM2-VL series, designed to process text and images with variable resolutions. Built on the LFM2 backbone, it extends the architecture for higher-capacity reasoning and stronger visual understanding while retaining efficiency.
3B125K ctx lfm1.03.6K 142Oct 2025- Same category
- Similar size (3B vs 3.3B)
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 3.3B)
- Commercial use OK
Transformers PaliGemma 3B weights, pre-trained with 224*224 input images and 128 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
2.9BGemma Terms of Use227.8K 748May 2024- Same category
- Similar size (2.9B vs 3.3B)
Fara1.5-4B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks…
4.5B256K ctx MIT2.8K 62Jul 2026- Same category
- Similar size (4.5B vs 3.3B)
- Commercial use OK
Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.
4.1B128K ctx MIT233.1K 750Aug 2024- Same category
- Similar size (4.1B vs 3.3B)
- Commercial use OK
We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
2.2B32K ctx Apache 2.0925.3K 531Aug 2024- Same category
- Similar size (2.2B vs 3.3B)
- Commercial use OK
Describe Anything Model 3B (DAM-3B) takes inputs of user-specified regions in the form of points/boxes/scribbles/masks within images, and generates detailed localized descriptions of images.
3Bnvidia-non-commercial-license7.7K 134Apr 2025- Same category
- Similar size (3B vs 3.3B)
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
2.1B256K ctx Apache 2.045.8K 126Oct 2025- Same category
- Similar size (2.1B vs 3.3B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
9.7B256K ctx Apache 2.06.3M 2.4KFeb 2026- Same category
- Larger (9.7B vs 3.3B)
- Commercial use OK
- Widely used
ZwZ2-4B is the Qwen3.5-4B-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.
4.5B256K ctx Unknown licence1.1K 12Oct 2026- Same category
- Similar size (4.5B vs 3.3B)
Intern-Decision-2B is a multimodal structured decision model fine-tuned from Qwen3.5-2B. 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.
2.2B256K ctx Apache 2.02K 19Sept 2026- Same category
- Similar size (2.2B vs 3.3B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.06M 1.3KOct 2025- Same category
- Larger (8.8B vs 3.3B)
- Commercial use OK
- Widely used
Transformers PaliGemma 2 3B weights fine-tuned on a mixture of academic tasks using 224×224 input images. PaliGemma 2 mix checkpoints are fine-tuned on a diverse set of tasks and are ready to use out of the box while pt checkpoints are pre-trained and intended for further fine-tuning.
3BGemma Terms of Use16.3K 73Nov 2024- Same category
- Similar size (3B vs 3.3B)
T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google, built by adapting pretrained decoder-only Gemma models into encoder-decoder ones.
2.1B32K ctx Gemma Terms of Use33.3K 88Oct 2025- Same category
- Similar size (2.1B vs 3.3B)