---
title: google/embeddinggemma-300m
description: "Model Page: EmbeddingGemma. Gemma 3, 303M parameters."
canonical_url: https://superlinked.com/models/google-embeddinggemma-300m
last_updated: 2026-05-25
---

# 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

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3876 · map at 10: 0.1471 · mrr at 10: 0.5895

**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/)