---
title: ibm-granite/granite-embedding-97m-multilingual-r2
description: "Model Summary: Granite-Embedding-97M-Multilingual-R2 is a 97M parameter dense embedding model from the Granite Embeddings collection for hig. ModernBERT, 97M parameters."
canonical_url: https://superlinked.com/models/ibm-granite-granite-embedding-97m-multilingual-r2
last_updated: 2026-08-24
---

# ibm-granite/granite-embedding-97m-multilingual-r2

Model Summary: Granite-Embedding-97M-Multilingual-R2 is a 97M parameter dense embedding model from the Granite Embeddings collection for high-quality multilingual text embeddings at minimal compute cost.

Source: [ibm-granite/granite-embedding-97m-multilingual-r2 on HuggingFace](https://huggingface.co/ibm-granite/granite-embedding-97m-multilingual-r2)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 97M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 384 |
| Max sequence length | 32,768 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | ar, az, bg, bn, ca, cs, da, de, el, en, es, et, fa, fi, fr, he, hi, hr, hu, id, is, it, ja, ka, kk, km, ko, lt, lv, mr, ms, nl, no, pl, pt, ro, ru, sk, sl, sq, sr, sv, sw, te, th, tl, tr, uk, ur, uz, vi, zh |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4468 · map at 10: 0.3847 · mrr at 10: 0.4362

**Performance (L4 b1 c16):** Corpus 50.5K tok/s · Corpus p50 28.9ms · Query 5.1K tok/s · Query p50 27.8ms

[Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Quality:** ndcg at 10: 0.3296 · map at 10: 0.2567 · mrr at 10: 0.2779

**Performance (L4 b1 c16):** Corpus 21.5K tok/s · Corpus p50 28.2ms · Query 2.8K tok/s · Query p50 27.3ms

[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:** ndcg at 10: 0.3434 · map at 10: 0.2699 · mrr at 10: 0.4132

**Performance (L4 b1 c16):** Corpus 52.4K tok/s · Corpus p50 29.2ms · Query 5.5K tok/s · Query p50 27.9ms

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

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Quality:** ndcg at 10: 0.7318 · map at 10: 0.6775 · mrr at 10: 0.6787

**Performance (L4 b1 c16):** Corpus 163.8K tok/s · Corpus p50 32.1ms · Query 7.7K tok/s · Query p50 27.7ms

[Reference](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.2920 · map at 10: 0.1022 · mrr at 10: 0.4834

**Performance (L4 b1 c16):** Corpus 104.0K tok/s · Corpus p50 30.1ms · Query 2.3K tok/s · Query p50 27.6ms

[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:** ndcg at 10: 0.2034 · map at 10: 0.1221 · mrr at 10: 0.3434

**Performance (L4 b1 c16):** Corpus 83.6K tok/s · Corpus p50 29.4ms · Query 5.2K tok/s · Query p50 28.2ms

[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:** ndcg at 10: 0.6860 · map at 10: 0.6390 · mrr at 10: 0.6507

**Performance (L4 b1 c16):** Corpus 95.2K tok/s · Corpus p50 31.0ms · Query 7.8K tok/s · Query p50 28.2ms

[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:** ndcg at 10: 0.8233 · map at 10: 0.7945 · mrr at 10: 0.7945

**Performance (L4 b1 c16):** Corpus 81.7K tok/s · Corpus p50 29.8ms · Query 116.4K tok/s · Query p50 30.2ms

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