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

← Catalog

fastino/gliner2-base-v1

Open comparison →

Primitive: /extract · Extract · extractor

> Extract entities, classify text, parse structured data, and extract relations—all in one efficient model.

Entities

Overview

Hardware: — drives latency, throughput & cost

Size208M params
Tasks /extract
Licenseapache-2.0
Languagesen
Latency135 ms
Throughput11.0K tok/s
Cost$0.020 /1M tok

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

Extraction

Output kindsEntities
Inputstext
Max sequence length512

Benchmarks

CoNLL-2003

news ner en

Named entity recognition on Reuters newswire text

Corpus: 3,453 Queries: 3,453
Quality
f1 0.5194
precision 0.4300
recall 0.6558
Performance L4 b1 c16
Extract 7.5K tok/s
Extract p50 141.6ms
Reference →

FewRel

general re en

Few-shot relation extraction from Wikipedia sentences

Corpus: 70,000 Queries: 70,000
Quality
f1 0.4000
precision 0.7622
recall 0.2711
Performance L4 b1 c16
Extract 14.5K tok/s
Extract p50 128.6ms
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.