Event date · · Tencent

Tencent open-sourced WeMM-Embedding-9B, a multimodal embedding model

Tencent 腾讯Chinese AIOpen weights
FACT STATEMENT

Tencent released WeMM-Embedding-9B, a universal multimodal embedding model built on Qwen3.5, on Hugging Face. It accepts text, images, videos, visual documents, and interleaved multimodal inputs, returning 4,096-dimensional L2-normalized embeddings. The model is licensed under Apache License 2.0.

China context

Original name
腾讯
Outside China
Open weights · huggingface.co
Claims
Company-reported; not yet independently evaluated
For builders
Builders outside China can integrate WeMM-Embedding-9B via Hugging Face Transformers or Sentence Transformers, and serve it with vLLM or SGLang, using Apache 2.0 licensed weights.
For investors
Tencent's release of a competitive open-weight multimodal embedding model under Apache 2.0 may pressure commercial embedding API providers and signal continued investment in open-source AI by Chinese tech giants.
What happened

Tencent released WeMM-Embedding-9B, a universal multimodal embedding model built on Qwen3.5, on Hugging Face. The model accepts text, images, videos, visual documents, and interleaved multimodal inputs, returning 4,096-dimensional L2-normalized embeddings. Audio input is not supported. The model is licensed under Apache License 2.0. Evaluation results on MMEB-v2 and MMEB-v3 benchmarks are provided in the model card.

Technical significance

WeMM-Embedding-9B is a 9B parameter multimodal embedding model built on Qwen3.5. It supports text, image, video, visual document, and interleaved multimodal inputs, producing 4,096-dimensional L2-normalized embeddings. The model supports Matryoshka embeddings via truncate_dim with renormalization. It can be served with vLLM 0.27.0 or SGLang 0.5.9. On MMEB-v2 (78 datasets), it achieves an average score of 80.6, with image Hit@1 of 81.9, video Hit@1 of 74.3, and visual document NDCG@5 of 83.3. On MMEB-v3 (190 tasks), it achieves V3-All score of 59.5, text NDCG@5 of 48.8, agent Hit@1 of 51.0, MCMR Hit@1 of 49.3, and audio Hit@1 of 0.0 (audio unsupported).

Industry impact

Developers outside China can now use a state-of-the-art open-weight multimodal embedding model from Tencent under Apache 2.0, reducing the cost and complexity of building retrieval systems for mixed text, image, and video content compared to closed-source alternatives.

Decision value

WeMM-Embedding-9B provides a permissively licensed, high-performance embedding model for multimodal retrieval, enabling businesses to build search and recommendation systems over diverse content types without vendor lock-in.

What to watch

Observable next signals include adoption of WeMM-Embedding-9B in open-source retrieval pipelines, community benchmarks comparing it to Qwen3-VL-Embedding and other models, and potential releases of larger or audio-capable variants by Tencent.

Latest in Chinese AI

  1. Moonshot AIReportedly: Qianwen Office adds 10 models including Qwen4-Max, Kimi-K3.1, GLM-5.3
  2. HuaweiReportedly: Huawei Kirin 9050 series chip details revealed: 30% audio performance boost, first H.266 hard decoding, low-latency AI heterogeneous computing
  3. AlibabaReportedly: Alibaba releases Qwen4-Max, a 2.4-trillion-parameter MoE flagship model with 1M-token context and over 60% lower task cost
  4. HuaweiReportedly: Huawei Cloud launches open-source Pangu model openPangu-2.1-Pro on MaaS platform
  5. Infinigence AIReportedly: D-Robotics and Infinigence AI Bring RLinf and Three Other Open-Source Robot Tools to Sunrise Chips

All China AI Events

AIGC Newsletter

China AI, with sources and context.

Analysis of Chinese AI models, companies and policy, and what you can use outside China.