# Tencent's WeChat Team Open-Sources a Multimodal Embedding Family Already Running in Production

The 2B, 4B and 9B models handle text, images, video and visual documents, and Tencent reports the 9B version scoring 80.6 overall on the MMEB-v3 evaluation.

- Published: 2026-08-28T06:11:21.137Z
- Canonical: https://polylog.news/ai/2026-08-28/tencent-s-wechat-team-open-sources-a-multimodal-embedding-fa
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [TechNode](https://technode.com/2026/08/27/wechat-team-open-sources-wemm-embedding-for-multimodal-search-and-recommendation/), [arXiv](https://arxiv.org/abs/2608.24053)

Tencent's WeChat vision team released WeMM-Embedding, a family of universal multimodal embedding models, with code, evaluation tooling and weights published on GitHub and Hugging Face and a technical report on arXiv. The release, reported i…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-28/tencent-s-wechat-team-open-sources-a-multimodal-embedding-fa (subscription information: https://polylog.news/pricing).