Tencent Open-Sources WeMM-Embedding: A Top-Ranked Multimodal Model
abhishek__AI · x · 2026-08-28
Tencent has open-sourced WeMM-Embedding, a multimodal embedding model powering WeChat.
Key Features:
- Multimodal Understanding: Supports unified embeddings for text, images, videos, and visual documents.
- Multiple Sizes: Available in 2B, 4B, and 9B parameter versions.
- SOTA Performance: Achieves #1 ranking on both MMEB-v2 and v3 benchmarks.
- Use Case: Specifically built for multimodal retrieval tasks.
The model is 100% open source, with code and weights publicly available.
Related event: Tencent Open-Sources WeMM-Embedding, Tops MMEB Leaderboard(3 posts)→
More from Models
- Meta releases Muse Spark Open: 816B open-weight model that runs on two M5 Ultra Mac Studios — op7418 · 2026-10-16
- Meta open-sources Muse Spark Open: 816B MoE that runs on two Mac Studios — op7418 · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16
- TRL adds day-0 support for fine-tuning Muse Spark Open's 816B MoE with LoRA on 64 H100s — QGallouedec · 2026-10-16
- Muse Spark Open eval configs revealed: inference parameters for GLM-5.3, Kimi K3, Qwen comparisons — evijit · 2026-10-16