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

← Catalog

Qwen/Qwen3-Embedding-8B

Open comparison →

Primitive: /encode · Encode · Qwen3

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

Long contextDense

Overview

Hardware: — drives latency, throughput & cost

Size7.6B params
Tasks /encode
Licenseapache-2.0
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: 4,096
Max sequence length40,960
Inputstext

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.5802
map at 10 0.5124
mrr at 10 0.5718
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.4110
map at 10 0.3229
mrr at 10 0.3768
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.6463
map at 10 0.5560
mrr at 10 0.7184
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
ndcg at 10 0.8486
map at 10 0.8092
mrr at 10 0.8092
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.4140
map at 10 0.1592
mrr at 10 0.6159
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.3270
map at 10 0.2092
mrr at 10 0.5011
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7871
map at 10 0.7394
mrr at 10 0.7477
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.9470
map at 10 0.9367
mrr at 10 0.9367
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 2.8K

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.