Sold by: Waltsoft Inc.
Deployed on AWS
21.7M monthly downloads. The only model combining dense, sparse, and ColBERT retrieval for 100+ languages. MTEB top-ranked for multilingual RAG.
Overview
BGE-M3 is BAAI's flagship multilingual retrieval model, uniquely combining three retrieval paradigms in a single model: dense embeddings for semantic similarity, sparse retrieval for keyword precision, and ColBERT multi-vector matching for fine-grained token-level relevance. With 21.7 million monthly downloads and top MTEB multilingual benchmark rankings, it is the most capable open-source model for enterprise multilingual RAG. Covering 100+ languages with an 8192-token context window, it serves as a single retrieval backbone for global document repositories where both semantic and keyword matching matter. Deployed on SageMaker with 1.1GB weights at 568M parameters, it handles enterprise knowledge bases, multilingual support systems, and cross-lingual search with a single endpoint.
Highlights
- Only open model combining dense + sparse + ColBERT retrieval -- three retrieval modes, one deployment
- 100+ languages with 8192-token context -- single endpoint replaces per-language retrieval stacks
- 21.7M monthly downloads; MTEB top-ranked multilingual retrieval model
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.10 |
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.10 |
Vendor refund policy
No refunds.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial release
Additional details
Inputs
- Summary
21.7M monthly downloads. The only model combining dense, sparse, and ColBERT retrieval for 100+ languages. MTEB top-ranked for multilingual RAG.
- Input MIME type
- application/json
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
Support
Vendor support
Contact support@waltsoft.net for deployment assistance.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Ask Sage is a secure, model and cloud-agnostic generative AI platform trusted by 15,000 government teams and 2,500 companies. Users have access to any commercial and government approved Large Language Model and various open-source models with ability to ingest CUI data, and integrate with existing systems via APIs. IL5/IL6 authorized with Top Secret deployments. Ask Sage is built with zero-trust architecture and label-based access control. Deploy on any cloud, on-premise, or air-gapped.
intfloat/multilingual-e5-base on SageMaker. 768-dimensional mean-pooled embeddings covering 100 languages. One endpoint for global-enterprise RAG -- no per-language model sprawl, no token billing.
939K monthly downloads. 5-star sentiment scoring for English, German, French, Spanish, Italian, and Dutch. For global brand monitoring and CX analytics.
8.6M monthly downloads. Smallest multilingual-E5 model at 117MB. High-throughput embedding for 100 languages in latency-constrained pipelines.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.