MMLForge Search models, datasets, tasks… Start free
Home › Models › Visual Document Retrieval › TomoroAI/tomoro-colqwen3-embed-4b
T

TomoroAI/tomoro-colqwen3-embed-4b

Visual Document Retrieval·TomoroAI· 74.7K· 31
transformers apache-2.0 Visual Document Retrieval 4.4B params

TomoroAI/tomoro-colqwen3-embed-4b is a state-of-the-art ColPali-style multimodal embedding model. It maps text queries, visual documents (images, PDFs) or short videos into aligned multi-vector embeddings.

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull TomoroAI/tomoro-colqwen3-embed-4b

Model details

Task
Visual Document Retrieval
Provider
TomoroAI
Framework
transformers
Parameters
4.4B
Size
8.3 GB
License
apache-2.0
Downloads
74.7K
Likes
31
Paper
arXiv:2407.01449
Updated
2025-12-07

About TomoroAI/tomoro-colqwen3-embed-4b

TomoroAI/tomoro-colqwen3-embed-4b is a state-of-the-art ColPali-style multimodal embedding model. It maps text queries, visual documents (images, PDFs) or short videos into aligned multi-vector embeddings.

Related Visual Document Retrieval

J jinaai/jina-embeddings-v4 Visual Document Retrieval ·3.8B params 634.7K 529 🤗 HF C vidore/colpali-v1.2 Visual Document Retrieval 309.8K 112 🤗 HF C vidore/colpali-v1.3-hf Visual Document Retrieval 287.9K 26 🤗 HF J jinaai/jina-embeddings-v4-vllm-retrieval Visual Document Retrieval ·3.8B params 179.4K 32 🤗 HF C athrael-soju/colqwen3.5-4.5B-v3 Visual Document Retrieval ·4.5B params 123.2K 11 🤗 HF C vidore/colqwen2-v1.0-hf Visual Document Retrieval ·2.2B params 94.3K 23 🤗 HF

Browse all Visual Document Retrieval models →