WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) 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-35BA3B
120 open-weight models that do the same job as WeMM-Video-35BA3B (36.2B 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.
Cohere Labs Aya Vision 32B is an open weights research release of a 32-billion parameter model with advanced capabilities optimized for a variety of vision-language use cases, including OCR, captioning, visual reasoning, summarization, question answering, code, and more.
33.1B8K ctx CC BY-NC 4.0296 227Mar 2025- Same category
- Similar size (33.1B vs 36.2B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
125BA10B256K ctx Apache 2.0706.9K 658Feb 2026- Same category
- Larger (125B vs 36.2B)
- Commercial use OK
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.
34.8B4K ctx Unknown licence2.5K 95Mar 2024- Same category
- Similar size (34.8B vs 36.2B)
We are releasing 🍨 Gelato-30B-A3B, a state-of-the-art grounding model for GUI computer-use tasks! Gelato is trained on our open-sourced Click-100k dataset and achieves 63.88% accuracy on ScreenSpot-Pro and 69.15% / 74.65% on OS-World-G / OS-World-G (Refined), surpassing prior specialized computer…
31.1BA3B256K ctx Apache 2.076 34Oct 2025- Same category
- Similar size (31.1B vs 36.2B)
- Commercial use OK
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.
27.5BDeepSeek License2.3K 410Dec 2024- Same category
- Similar size (27.5B vs 36.2B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
29.4BA3BApache 2.0260 42Jun 2025- Same category
- Similar size (29.4B vs 36.2B)
- Commercial use OK
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding.
124BA12B1M ctx openmdw-1.182.2K 134Oct 2026- Same category
- Larger (124B vs 36.2B)
- 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
- Smaller (8.8B vs 36.2B)
- Commercial use OK
- Widely used
As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so.
180BA61.6B256K ctx qwen-community-1.02.7M 7.5KAug 2026- Same category
- Larger (180B vs 36.2B)
- Widely used
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.
73.4B125K ctx Qwen License45.8K 668Jan 2025- Same category
- Larger (73.4B vs 36.2B)
ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.
9.7B32K ctx Apache 2.0339K 43Apr 2026- Same category
- Smaller (9.7B vs 36.2B)
- Commercial use OK
Developer: Microsoft Corporation Authorized Representative: Microsoft Ireland Operations Limited, 70 Sir John Rogerson's Quay, Dublin 2, D02 R296, Ireland Release Date: March 4, 2026 License: MIT Parameters: 15B Context Length: 16,384 tokens Inputs: Text and Images Outputs: Text Training GPUs: 240…
15.1B32K ctx MIT9.5K 185Jan 2026- Same category
- Smaller (15.1B vs 36.2B)
- Commercial use OK
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
- Smaller (10B vs 36.2B)
- Commercial use OK
Transformers PaliGemma 2 28B weights, pre-trained with 896*896 input images and 512 token input/output text sequences. The model is available in the bfloat16 format for fine-tuning.
27.7BGemma Terms of Use753 52Nov 2024- Same category
- Similar size (27.7B vs 36.2B)
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities—all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B).
16.4BA3B128K ctx MIT31.3K 286Apr 2025- Same category
- Smaller (16.4B vs 36.2B)
- Commercial use OK
This is an updated version of Kimi-VL-A3B-Thinking, with following improved abilities:
16.4BA3B128K ctx MIT13.4K 391Jun 2025- Same category
- Smaller (16.4B vs 36.2B)
- 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 2.0266.5K 163Feb 2026- Same category
- Smaller (9.7B vs 36.2B)
- 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.
12.2B128K ctx Gemma Terms of Use405.7K 925Mar 2025- Same category
- Smaller (12.2B vs 36.2B)
LLaDA-UI is an MoE-based, block-wise diffusion vision-language GUI agent. It understands screenshots at their native aspect ratio and produces grounded coordinates or structured actions for mobile, desktop, and web interfaces.
16.9BA2.1B8K ctx Unknown licence288 24Sept 2026- Same category
- Smaller (16.9B vs 36.2B)
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 2.038.7K 83Oct 2026- Same category
- Smaller (9.4B vs 36.2B)
- Commercial use OK
Yi-VL adopts the LLaVA architecture, which is composed of three primary components:
34B4K ctx Apache 2.0615 265Dec 2023- Same category
- Similar size (34B vs 36.2B)
- Commercial use OK
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 2.033.3K 934Sept 2026- Same category
- Smaller (9.4B vs 36.2B)
- Commercial use OK
We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.
78.4B32K ctx Qwen License11.7K 239Apr 2025- Same category
- Larger (78.4B vs 36.2B)
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 MIT36K 715Sept 2026- Same category
- Smaller (9.4B vs 36.2B)
- Commercial use OK