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

← Catalog

mixedbread-ai/mxbai-embed-large-v1

Open comparison →

Primitive: /encode · Encode · BERT

The crispy sentence embedding family from Mixedbread.

Dense

Overview

Hardware: — drives latency, throughput & cost

Size335M params
Tasks /encode
Licenseapache-2.0
Languagesen
Latency
Throughput
Cost /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Embedding

Output typesDense
Dimensionsdense: 1,024
Max sequence length512
Inputstext

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.4737
map at 10 0.4126
mrr at 10 0.4677
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.3420
map at 10 0.2647
mrr at 10 0.2754
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.4531
map at 10 0.3715
mrr at 10 0.5352
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
ndcg at 10 0.7530
map at 10 0.7029
mrr at 10 0.7025
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3865
map at 10 0.1519
mrr at 10 0.5816
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.2308
map at 10 0.1406
mrr at 10 0.3761
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7389
map at 10 0.6925
mrr at 10 0.7027
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.8086
map at 10 0.7787
mrr at 10 0.7787
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.1K

Contact us

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

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.