# Multilingual embedding

Qwen3-Embedding-8B is the latest proprietary model in the Qwen family, designed for text embedding and ranking tasks. It is built on the dense base model of the Qwen3 series and has excellent multilingual capabilities and long text understanding capabilities.

This is the Qwen3-Embedding-4B model after GPTQ quantization, with significantly reduced video memory usage and minimal performance loss.

Multilingual E5 large pooled model supporting sentence similarity calculation and feature extraction tasks in multiple languages.

This is a sentence-transformers model fine-tuned from intfloat/multilingual-e5-small, trained with Korean query-passage pairs to enhance performance in Korean retrieval tasks.

Jina Embeddings v4 is a general-purpose embedding model designed for multimodal and multilingual retrieval, especially suitable for retrieving complex documents, including visually rich documents containing charts, tables, and illustrations.

A quantized version of the multilingual embedding model developed by the IBM Granite team, supporting text embedding tasks in 17 languages, suitable for scenarios such as retrieval and information extraction.

The ONNX INT8 quantized version of BAAI/bge-m3, suitable for dense retrieval tasks, and optimizes compatibility with Vespa Embedding.

This model is used to generate sentence embeddings for Sanskrit and Tibetan, suitable for semantic similarity tasks.