Sold by: Waltsoft Inc.
Deployed on AWS
72.9M monthly downloads. The most deployed open reranker. Re-scores top-K retrieval results for precision RAG on CPU in under 10ms per query.
Overview
MS-MARCO MiniLM-L-6-v2 is the world's most downloaded open-source cross-encoder reranker with 72.9 million monthly downloads -- it is the de facto standard reranking layer in production RAG pipelines. Fine-tuned on Microsoft's MS-MARCO dataset with 500K human-labeled passage relevance judgments, it dramatically improves retrieval precision when placed between your vector store and your LLM. At only 90MB, it is the lightest cross-encoder that still delivers near-oracle reranking quality, making it the first choice for latency-sensitive chatbots, enterprise search, and document Q&A systems. Under 10ms per query on ml.m5.xlarge. Drop-in compatible with LangChain, LlamaIndex, and Haystack reranking APIs.
Highlights
- 72.9M monthly downloads -- the most deployed open-source reranker in production RAG systems worldwide
- 90MB model size with sub-10ms CPU inference -- the fastest precision upgrade for any vector search pipeline
- Fine-tuned on 500K MS-MARCO relevance judgments; compatible with LangChain, LlamaIndex, and Haystack
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
72.9M monthly downloads. The most deployed open reranker. Re-scores top-K retrieval results for precision RAG on CPU in under 10ms per query.
- 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
2.9M monthly downloads. Deeper 12-layer cross-encoder reranker for higher-accuracy RAG. Optimal precision-throughput balance for enterprise search.
BAAI/bge-reranker-base cross-encoder on SageMaker. Second-stage reranking lifts RAG answer precision by 3-8 nDCG@10 points over embedding-only retrieval. Flat $0.08/hr, no per-query charges.
sentence-transformers/all-MiniLM-L6-v2 on SageMaker. 384-dimensional mean-pooled embeddings, 90MB model, 160M+ monthly downloads. Embed over 15,000 sentences per minute on ml.m5.xlarge at $0.07/hr.
A fast neural text reranking model supporting 8192 sequence length
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.