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

← Catalog

mixedbread-ai/mxbai-colbert-large-v1

Open comparison →

Primitive: /score · Score · BERT

The crispy rerank family from Mixedbread.

Overview

Hardware: — drives latency, throughput & cost

Size335M params
Tasks /encode · /score
Licenseapache-2.0
Latency46 ms
Throughput4.0K tok/s
Cost$0.056 /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 length512

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6299
map at 10 0.4759
mrr at 10 0.7179
Reference →

CMedQAv1-reranking

general reranking en

Quality
ndcg at 10 0.2169
map at 10 0.1628
mrr at 10 0.2239

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Performance L4 b1 c16
Corpus 30.0K tok/s
Corpus p50 68.7ms
Query 3.3K tok/s
Query p50 49.0ms
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Corpus 12.5K tok/s
Corpus p50 62.5ms
Query 2.2K tok/s
Query p50 43.6ms
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Corpus 35.0K tok/s
Corpus p50 71.8ms
Query 4.2K tok/s
Query p50 44.7ms
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Performance L4 b1 c16
Corpus 77.3K tok/s
Corpus p50 101.4ms
Query 5.9K tok/s
Query p50 45.0ms
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Performance L4 b1 c16
Corpus 51.3K tok/s
Corpus p50 92.4ms
Query 1.8K tok/s
Query p50 44.1ms
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Performance L4 b1 c16
Corpus 36.2K tok/s
Corpus p50 81.3ms
Query 3.8K tok/s
Query p50 46.5ms
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Corpus 46.8K tok/s
Corpus p50 89.5ms
Query 5.7K tok/s
Query p50 46.2ms
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Performance L4 b1 c16
Corpus 45.2K tok/s
Corpus p50 78.9ms
Query 69.9K tok/s
Query p50 64.7ms
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.