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.
LFM2.5‑VL-1.6B is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-1.6B, built on an updated backbone LFM2.5-1.2B-Base and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.
1.6B125K ctx lfm1.010.4K 334Jan 2026- Same category
- Smaller (1.6B vs 3.3B)
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 2.082.9K 42Jul 2026- Same category
- Larger (10B vs 3.3B)
- 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.
2.4B32K ctx Apache 2.02.8K 41Jan 2025- Same category
- Similar size (2.4B vs 3.3B)
- Commercial use OK
The H2OVL-Mississippi-2B is a high-performing, general-purpose vision-language model developed by H2O.ai to handle a wide range of multimodal tasks.
2.2B8K ctx Apache 2.019.2K 46Oct 2024- Same category
- Similar size (2.2B vs 3.3B)
- 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
- Larger (7.8B vs 3.3B)
- Commercial use OK
LFM2.5-VL-1.6B-Extract extracts user-defined fields from images and returns them as JSON. It is Liquid AI's first vision model in the Liquid Nanos collection—compact, task-specific models built for production workflows—and extends the Extract family alongside LFM2-1.2B-Extract for text documents.
1.6B125K ctx lfm1.02.2K 72May 2026- Same category
- Smaller (1.6B vs 3.3B)
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.0135.3K 235Oct 2025- Same category
- Larger (8.8B vs 3.3B)
- Commercial use OK
BLIP-2 model, leveraging Flan T5-xl (a large language model). It was introduced in the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models by Li et al. and first released in this repository.
3.9B512 ctx MIT19.1K 95Feb 2023- Same category
- Similar size (3.9B vs 3.3B)
- Commercial use OK
This section describes the MedGemma model and how to use it.
4.3B128K ctx health-ai-developer-foundations556 165May 2025- Same category
- Similar size (4.3B vs 3.3B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.0881.9K 141Feb 2026- Same category
- Smaller (873M vs 3.3B)
- 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 2.053.3K 201Dec 2025- Same category
- Larger (8.7B vs 3.3B)
- 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 2.0229.8K 624Apr 2025- Same category
- Larger (8.3B vs 3.3B)
- 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 License60K 265Dec 2025- Same category
- Larger (8.8B vs 3.3B)
- Commercial use OK
Transformers PaliGemma 3B weights, pre-trained with 448*448 input images and 512 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
2.9BGemma Terms of Use1.7K 35May 2024- Same category
- Similar size (2.9B vs 3.3B)
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels. It achieves comparable performance to SOTA MLLMs Qwen2-VL and InternVL2.5 on question-answering benchmarks.
3.9B32K ctx Apache 2.0470 99Jan 2025- Same category
- Similar size (3.9B vs 3.3B)
- Commercial use OK
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 2.0309.6K 66Feb 2025- Same category
- Larger (8.3B vs 3.3B)
- Commercial use OK
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 2.096.9K 109Aug 2025- Same category
- Larger (8.5B vs 3.3B)
- Commercial use OK
Transformers PaliGemma 3B weights, pre-trained with 896*896 input images and 512 token input/output text sequences. The models are available in float32, bfloat16 and float16 formats for fine-tuning.
2.9BGemma Terms of Use1.5K 126May 2024- Same category
- Similar size (2.9B vs 3.3B)
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 2.09.3K 191Jul 2026- Same category
- Larger (8.9B vs 3.3B)
- Commercial use OK
Transformers PaliGemma 3B weights, fine-tuned with 448*448 input images and 512 token input/output text sequences on a mixture of downstream academic datasets. The models are available in float32, bfloat16 and float16 format for research purposes only.
2.9BGemma Terms of Use1.1K 121May 2024- Same category
- Similar size (2.9B vs 3.3B)
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 licence6.5K 49Aug 2026- Same category
- Larger (9B vs 3.3B)
LFM2‑VL is Liquid AI's first series of multimodal models, designed to process text and images with variable resolutions. Built on the LFM2 backbone, it is optimized for low-latency and edge AI applications.
1.6B125K ctx lfm1.09.2K 234Aug 2025- Same category
- Smaller (1.6B vs 3.3B)
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 License144K 188Jun 2025- Same category
- Larger (8.7B vs 3.3B)
- Commercial use OK
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
8.7B40K ctx Apache 2.067.7K 1.1KAug 2025- Same category
- Larger (8.7B vs 3.3B)
- Commercial use OK