Why did we open-source our inference engine? Read the post

mixedbread-ai/mxbai-rerank-base-v2 (Score)

Architecture
Parameters
150M
Tasks
Score
Outputs
Score
Max Sequence Length
8,192 tokens
License

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Performance L4 b1 c16
Query TPS 4.1K
Query p50 593.2ms

CosQA

technology retrieval en

Performance L4 b1 c16
Query TPS 2.1K
Query p50 444.7ms

LegalBenchConsumerContractsQA

legal retrieval en

Performance L4 b1 c16
Query TPS 14.6K
Query p50 450.9ms

SCIDOCS

scientific retrieval en

Performance L4 b1 c16
Query TPS 7.0K
Query p50 457.1ms

StackOverflowQA

technology retrieval en

Performance L4 b1 c16
Query TPS 11.4K
Query p50 534.8ms

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.

Github
1.5K

Contact us

Tell us about your use case and we'll get back to you shortly.