ColBERT multi-vector retrieval
Captured config identifies HF_ColBERT with a bert model type, and hub tags mark multi-vector ColBERT sentence-similarity use.
Open Source Model Profile · mixedbread-ai
mxbai-colbert-large-v1
mxbai-colbert-large-v1 is a 335M-parameter ColBERT retrieval model from mixedbread-ai. According to the model card, it builds on mxbai-embed-large-v1.
- Publisher
- mixedbread-ai
- Task
- sentence-similarity
- Model type
- bert
- License
- apache-2.0
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
mxbai-colbert-large-v1 is published by mixedbread-ai as a bert-based sentence-similarity model. The captured configuration identifies HF_ColBERT, and Safetensors metadata reports 335272960 parameters. According to the model card, it is the publisher's first English ColBERT model, built upon mxbai-embed-large-v1.
Recorded capabilities
mxbai-embed-large-v1 foundation
According to the model card, this English ColBERT model is built upon mixedbread-ai/mxbai-embed-large-v1.
Publisher-reported retrieval comparison
The model card compares the model against ColBERTv2 and Jina-ColBERT-v1 across retrieval datasets, reporting an average of 50.37 versus 43.08 and 49.82.
Use cases in the source record
- English passage retrieval and reranking experiments using the publisher's documented ColBERT multi-vector workflow.
Limitations and unknowns
- No independently measured evaluation results were extracted; comparison figures are publisher-reported card claims.
- No context-window, dimension, or training-data values were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: mixedbread-ai/mxbai-colbert-large-v1
Captured: Unknown. Processed: 2026-09-07T19:34:52.168558+00:00.
The crispy rerank family from Mixedbread . 🍞 Looking for a simple end-to-end retrieval solution? Meet Omni, our multimodal and multilingual model. Get in touch for access. mixedbread-ai/mxbai-colbert-large-v1 This is our first English ColBERT model, which is built upon our sentence embedding model mixedbread-ai/mxbai-embed-large-v1 . You can learn more about the models in our blog post . Quickstart Using Sentence Transformers This checkpoint also loads with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the MultiVectorEncoder . pip install "sentence-transformers>=6.0.0" from sentence_transfor…
F001F002F003F004F005F006F007F009F010F014F017