WeMM-Video
A bilingual (Chinese and English) Tencent family for joint understanding of video and sound: it takes text, images, audio and video, and answers in text. It can match frames with the original soundtrack, describe what is happening, transcribe speech and reason about what is seen and heard; it also works with silent video, standalone audio and images. Three sizes: a dense 2B, 9B and a 35B-A3B MoE (3B active). Compressed FP8, AWQ, GGUF and NVFP4 versions exist. Russian is not stated.
- Developer
- Tencent (WeChat), China
- First release
- Nov 2026
- Latest release
- Nov 2026
- Sizes
- 2B, 9B and 35B-A3B
- License
- Commercial use allowedApache 2.0
- Russian
- Not supported
- Running
- On your own serverNeeds a GPU
- Industries
- Media and production, Customer support, Security
What it does
- describing and analysing video together with sound
- transcribing speech and questions about a recording
- checking and moderating video content
Where it is used
Hardware requirements
Versions
- WeMM-Video-35B-A3B (BF16, FP8, AWQ, GGUF, NVFP4)
- WeMM-Video-9B
- WeMM-Video-2B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can WeMM-Video be used in a commercial project?
Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does WeMM-Video need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does WeMM-Video support Russian?
No. The developer documentation lists the supported languages and Russian is not among them.
Where can I download WeMM-Video and what does it cost?
The WeMM-Video weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Models that understand text, images, audio and video and reply by voice in real time. Qwen3-Omni speaks 10 languages, including Russian.
DetailsImage + textWeVisOne-VLWeChat Vision, Tencent · ChinaCommercial use allowedA unified vision model from WeChat Vision (Tencent) based on Qwen3-VL: one model does both object search and precise perception. It finds objects by description, points to the needed item, counts items, marks points, reads text, and at the pixel level cuts out an object by description and makes an alpha matte on request, for which a small 9.6M-parameter decoder was added to the model. Two sizes, 2B and 4B. It suits image labeling, cutting products out of a background and counting items in a photo. Prompt languages are not stated on the card.
DetailsVoice assistantsMiniCPM-oOpenBMB (ModelBest, Tsinghua University) · ChinaCommercial use allowedA small model that sees, hears and replies by voice in real time, and can clone a voice. Voice dialogue in English and Chinese, text in 30+ languages.
DetailsSource: huggingface.co/tencent/WeMM-Video-35BA3B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


