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

← Catalog

mixedbread-ai/mxbai-edge-colbert-v0-32m

Open comparison →

Primitive: /score · Score · ModernBERT

The crispy, lightweight ColBERT family from Mixedbread.

Long context

Overview

Hardware: — drives latency, throughput & cost

Size32M params
Tasks /encode · /score
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.

Scoring

Inputstext
Max sequence length8,192

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.5270
map at 10 0.3626
mrr at 10 0.6088
Reference →

CMedQAv1-reranking

general reranking en

Quality
ndcg at 10 0.2974
map at 10 0.2385
mrr at 10 0.3151

CMedQAv2-reranking

general reranking en

Quality
ndcg at 10 0.3143
map at 10 0.2534
mrr at 10 0.3350

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.4085
map at 10 0.3530
mrr at 10 0.4184
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.2817
map at 10 0.2095
mrr at 10 0.2271
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.3671
map at 10 0.2868
mrr at 10 0.4356
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
ndcg at 10 0.6842
map at 10 0.6258
mrr at 10 0.6315
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
ndcg at 10 0.1659
map at 10 0.1394
mrr at 10 0.1394
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3570
map at 10 0.2609
mrr at 10 0.5680
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.1597
map at 10 0.0897
mrr at 10 0.2878
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7094
map at 10 0.6627
mrr at 10 0.6819
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.5188
map at 10 0.4640
mrr at 10 0.4769
Reference →

T2Reranking

general reranking zh

Chinese passage ranking benchmark

Quality
ndcg at 10 0.6764
map at 10 0.4979
mrr at 10 0.7179
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.