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

← Catalog

Qwen/Qwen3-VL-Embedding-2B

Open comparison →

Primitive: /encode · Encode · Qwen3-VL

The Qwen3-VL-Embedding and Qwen3-VL-Reranker model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model.

MultimodalLong contextDense

Overview

Hardware: — drives latency, throughput & cost

Size2.1B params
Tasks /encode
Licenseapache-2.0
Latency36 ms
Throughput494 tok/s
Cost$0.450 /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: 2,048
Max sequence length32,768
Inputstext · image · video

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.4939
map at 10 0.4281
mrr at 10 0.4828
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.3448
map at 10 0.2677
mrr at 10 0.2959
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.3793
map at 10 0.3051
mrr at 10 0.4542
Performance L4 b1 c4
Corpus 494 tok/s
Corpus p50 35.9ms
Reference →

Flickr30kI2TRetrieval

general retrieval en

Image-to-text retrieval: retrieve captions from images

Corpus: 31,783 Queries: 1,000
Quality
ndcg at 10 0.8751
map at 10 0.8017
mrr at 10 0.9653
Performance L4 b1 c4
Corpus 494 tok/s
Corpus p50 35.9ms
Query 0.0 mpix/s
Query p50 4.3s
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
ndcg at 10 0.7516
map at 10 0.6943
mrr at 10 0.6943
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3689
map at 10 0.1432
mrr at 10 0.5699
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.2090
map at 10 0.1250
mrr at 10 0.3423
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7384
map at 10 0.6892
mrr at 10 0.6994
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
ndcg at 10 0.9056
map at 10 0.8888
mrr at 10 0.8888
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 3.3K

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.