---
title: ibm-granite/granite-embedding-small-english-r2
description: "Model Summary: Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection . ModernBERT, 48M parameters."
canonical_url: https://superlinked.com/models/ibm-granite-granite-embedding-small-english-r2
last_updated: 2026-06-05
---

# ibm-granite/granite-embedding-small-english-r2

Model Summary: Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings.

Source: [ibm-granite/granite-embedding-small-english-r2 on HuggingFace](https://huggingface.co/ibm-granite/granite-embedding-small-english-r2)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 48M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 384 |
| Max sequence length | 8,192 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Quality:** map at 10: 0.2733 · mrr at 10: 0.3107 · ndcg at 10: 0.3530

[Reference](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Quality:** map at 10: 0.2614 · mrr at 10: 0.3941 · ndcg at 10: 0.3317

[Reference](https://sites.google.com/view/fiqa/)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3016 · map at 10: 0.1115 · mrr at 10: 0.5082

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Quality:** map at 10: 0.0595 · mrr at 10: 0.1655 · ndcg at 10: 0.1026

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Quality:** map at 10: 0.6724 · mrr at 10: 0.6832 · ndcg at 10: 0.7157

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

Programming question answering from Stack Overflow

Corpus: 19,931 · Queries: 1,994

**Quality:** map at 10: 0.8818 · mrr at 10: 0.8818 · ndcg at 10: 0.9005

[Reference](https://arxiv.org/abs/2407.02883)