Search and RAGComputer vision

Trident

Embeddings for mixed-modality search: text, images and pages with text and a picture together land in one space, and a single text query can rank them in one shared list. Built on research showing that ordinary models prefer text over images. Language on the card: English.

Developer
OpenBMB, China
First release
Oct 2026
Latest release
Oct 2026
Sizes
2B (based on Qwen3-VL-2B)
License
Commercial use allowedMIT
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Documents and accounting, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • searching a catalog where some items are described by text and some by a picture
  • searching slide decks and pages with diagrams
  • RAG over a mixed knowledge base

Where it is used

online stores and catalogsdocument management and knowledge basesmedia and archives

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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Trident-Qwen3VL-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 Trident be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Trident 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 Trident support Russian?

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

Where can I download Trident and what does it cost?

The Trident 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

Visual document searchEVIETencent · ChinaCommercial use allowed

Finds the right pages in documents as pictures, without turning them into text: matches a query against how the page looks. Version 8B scores 66.75 on ViDoRe V3. The index can be compressed to 32 vectors per page.

DetailsSearch and RAGWeMM-EmbeddingTencent · ChinaCommercial use allowed

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.

DetailsSearch 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.

Details

Source: huggingface.co/openbmb/Trident-Qwen3VL-2B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.