TomoroAI/tomoro-colqwen3-embed-4b is an advanced ColPali-style multimodal embedding model that can map text queries, visual documents (such as images, PDFs) or short videos into aligned multi-vector embeddings. This model combines the advantages of Qwen3-VL-4B-Instruct and Qwen3-Embedding-4B, performs excellently in the ViDoRe benchmark test, and significantly reduces the embedding space occupation.

MultimodalTransformersOther

This is a compressed version of Qwen/Qwen3-Embedding-0.6B using llm-compressor, adopting the W8A8 quantization scheme. This model significantly reduces the storage and computational resource requirements while maintaining performance, and is suitable for feature extraction tasks in resource-constrained environments.

Natural Language ProcessingSafetensorsMultiple Languages

This is a 4-bit quantized version converted from the Qwen3-Embedding-0.6B model, optimized for the MLX framework.

Natural Language ProcessingMlx

Qwen3-Embedding-8B is an 8-billion parameter text embedding model developed by the Tongyi Qianwen team at Alibaba. It is optimized and implemented based on the MLX library and is specifically designed for sentence similarity calculation and text feature extraction tasks.

Natural Language ProcessingMlx

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.

Natural Language ProcessingSentence-transformers

Qwen3-Embedding-4B is a text embedding model built on the Qwen3 series, designed specifically for text embedding and ranking tasks, and performs excellently in multilingual text processing and code retrieval.

Natural Language ProcessingSentence-transformers

This is a quantized model based on ONNX, which is the uint8 quantized version of Qwen/Qwen3-Embedding-0.6B. It reduces the model size while maintaining retrieval performance.

Natural Language ProcessingSentence-transformers

This is a 4-bit DWQ quantized version converted from Qwen/Qwen3-Embedding-8B, suitable for the embedding model of the MLX framework.

Natural Language ProcessingMlx

The Qwen3 Embedding model series is the latest self-developed model of the Tongyi family, designed specifically for text embedding and ranking tasks, supporting more than 100 languages, and ranking first on the MTEB multilingual leaderboard.

Natural Language ProcessingSentence-transformers

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

Natural Language ProcessingSentence-transformers

GPTQ quantized version of Qwen3-Embedding-8B, significantly reducing VRAM requirements while maintaining high performance

Natural Language ProcessingSentence-transformers

GPTQ quantized version of Qwen3-Embedding-0.6B, optimized for video memory usage with minimal performance loss

Natural Language ProcessingSentence-transformers

This is a 4-bit quantized version converted from the Qwen3-Embedding-4B model, optimized for the MLX framework

Natural Language ProcessingMlx

This is a 4-bit deep quantization version of the Qwen3-Embedding-0.6B model, optimized for the MLX framework. The model provides efficient text embedding generation capabilities and is suitable for various natural language processing tasks.

Natural Language ProcessingMlx