Tencent's SOTA Gemma3-12B-based multilingual embedder, #1 on MMTEB as of November 2025.
Access model weights, configuration files, and documentation.
See which devices can run this model and at what quality level.
Tencent's 11.8B embedding model fine-tuned from Gemma 3 12B using the KaLM-Embedding V2 recipe with Matryoshka Representation Learning across seven embedding dimensions (3840 down to 64). Ranked #1 on MMTEB at release with a 72.32 mean task score, surpassing Qwen3-Embedding-8B and gemini-embedding-001; supports both sentence-transformers and vLLM via a CausalLM branch.
View on Hugging Face