---
title: ibm-granite/granite-embedding-30m-sparse
description: "Model Summary: Granite-Embedding-30m-Sparse is a 30M parameter sparse biencoder embedding model from the Granite Experimental suite that can. RoBERTa, 30M parameters."
canonical_url: https://superlinked.com/models/ibm-granite-granite-embedding-30m-sparse
last_updated: 2026-06-10
---

# ibm-granite/granite-embedding-30m-sparse

Model Summary: Granite-Embedding-30m-Sparse is a 30M parameter sparse biencoder embedding model from the Granite Experimental suite that can be used to generate high quality text embeddings.

Source: [ibm-granite/granite-embedding-30m-sparse on HuggingFace](https://huggingface.co/ibm-granite/granite-embedding-30m-sparse)

## Overview

| Field | Value |
|-------|-------|
| Architecture | RoBERTa |
| Parameters | 30M |
| Tasks | Encode |
| Outputs | Sparse |
| Dimensions | Sparse: 50,265 |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Performance (L4 b1 c16):** Corpus 22.8K tok/s · Corpus p50 94.5ms · Query 3.7K tok/s · Query p50 46.3ms

[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

**Performance (L4 b1 c16):** Corpus 13.9K tok/s · Corpus p50 59.0ms · Query 2.1K tok/s · Query p50 45.2ms

[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

**Performance (L4 b1 c16):** Corpus 25.0K tok/s · Corpus p50 106.9ms · Query 4.1K tok/s · Query p50 46.3ms

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

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Performance (L4 b1 c16):** Corpus 69.5K tok/s · Corpus p50 112.3ms · Query 5.7K tok/s · Query p50 46.7ms

[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: 0.3147 · map at 10: 0.1224 · mrr at 10: 0.5112

**Performance (L4 b1 c16):** Corpus 42.5K tok/s · Corpus p50 105.3ms · Query 1.0K tok/s · Query p50 51.6ms

[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

**Performance (L4 b1 c16):** Corpus 30.3K tok/s · Corpus p50 103.1ms · Query 3.9K tok/s · Query p50 45.5ms

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

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Performance (L4 b1 c16):** Corpus 40.6K tok/s · Corpus p50 105.1ms · Query 5.9K tok/s · Query p50 45.7ms

[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

**Performance (L4 b1 c16):** Corpus 33.6K tok/s · Corpus p50 109.4ms · Query 44.1K tok/s · Query p50 111.7ms

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