---
title: google/embeddinggemma-300m
description: "Model Page: EmbeddingGemma. Gemma 3, 303M parameters."
canonical_url: https://superlinked.com/models/google-embeddinggemma-300m
last_updated: 2026-06-15
---

# google/embeddinggemma-300m

Model Page: EmbeddingGemma

Source: [google/embeddinggemma-300m on HuggingFace](https://huggingface.co/google/embeddinggemma-300m)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Gemma 3 |
| Parameters | 303M |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 768 |
| Max sequence length | 2,048 tokens |
| License | gemma |
| Inputs | text |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4733 · map at 10: 0.4090 · mrr at 10: 0.4670

[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: 0.3981 · map at 10: 0.3067 · mrr at 10: 0.3095

[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: 0.2649 · map at 10: 0.2011 · mrr at 10: 0.3240

[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: 0.8032 · map at 10: 0.7513 · mrr at 10: 0.7500

[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: 0.2619 · map at 10: 0.0815 · mrr at 10: 0.4417

**Performance (L4 b1 c16):** Corpus 27.2K tok/s · Corpus p50 86.8ms · Query 540 tok/s · Query p50 82.0ms

**Performance (RTX-4090 b1 c16):** Corpus 79.6K tok/s · Corpus p50 55.7ms · Query 1.9K tok/s · Query p50 27.8ms

[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: 0.1092 · map at 10: 0.0598 · mrr at 10: 0.1956

[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: 0.7054 · map at 10: 0.6565 · mrr at 10: 0.6670

[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: 0.6961 · map at 10: 0.6744 · mrr at 10: 0.6744

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