WeChat's new embeddings unify text, video, images and documents in one space
Tencent WeChat's vision team open-sourced WeMM-Embedding, a family of multimodal embedding models (2B/4B/9B) that map text, images, video, visual documents, and interleaved inputs into one representation space. Across 78 benchmarks it tops earlier leaders like Qwen3-VL-Embedding and GME, per the technical report. Matryoshka dimensions let you truncate to as few as 64; at 256, the 2B model keeps 98.7% of its full-size image and video performance. Weights are on Hugging Face, with vLLM and SGLang serving supported.