Search and RAGComputer vision

WeMM-Embedding

Universal embeddings based on Qwen3.5: they turn text, images, video and visual documents into one vector of 4096 numbers. Audio is not supported. Languages on the card: Chinese and English.

Developer
Tencent, China
First release
Aug 2026
Latest release
Aug 2026
Sizes
2B и 9B
License
Commercial use allowedApache 2.0 except third-party components (their terms are in the LICENSE file)
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Media and production, Documents and accounting, Customer support
Deploy on your server Hugging Face

What it does

  • searching a product catalog by picture or description
  • searching video and slide decks
  • RAG over mixed text and image materials

Where it is used

online storesmedia and archivesknowledge bases

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. WeMM-Embedding-9B
  2. WeMM-Embedding-2B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

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-Embedding be used in a commercial project?

Yes. License: Apache 2.0 except third-party components (their terms are in the LICENSE file). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does WeMM-Embedding 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-Embedding support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download WeMM-Embedding and what does it cost?

The WeMM-Embedding 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

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Search and RAGEmbeddingGemmaGoogle · USACommercial use with conditions

Small multilingual embeddings from Google that run on a phone or laptop without internet. The second version also understands images, video and audio in one vector space.

DetailsSearch and RAGQwen3 Embedding / RerankerAlibaba (Qwen) · ChinaCommercial use allowed

Embeddings and rerankers based on Qwen3, among the best open ones for multilingual search, including Russian. VL versions search images, screenshots and video.

DetailsVisual document searchGME (General Multimodal Embedding)Alibaba (Tongyi Lab) · ChinaCommercial use allowed

One vector for text, for an image and for a text-image pair: a single model can find a product by photo, a document page by question and an image by description. The card lists English and Chinese.

Details

Source: huggingface.co/tencent/WeMM-Embedding-9B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.