Back to Models
Google Deep MindConditional Open

EmbeddingGemma - 300M

EmbeddingGemma - 300M is an embedding model developed by Google DeepMind. It enables efficient vector representations and is suitable for semantic search and classification of text data.

Parameters

3.0B

Context Window

2K

License

Gemma License

Release Date

2025-09-05

API Pricing

API pricing for this model is not yet available

Strengths

  • Developed by Google DeepMind
  • Lightweight model size
  • Efficient vector transformation

Weaknesses

  • Short context length of 2K
  • Limited parameter scale
  • Specialized model, not general-purpose

Use Cases

  • Implementing semantic search
  • Assessing document similarity
  • Text clustering

Deep Analysis

Parameters

308M

MTEB Multilingual

61.15

SOTA for sub-500M

MTEB English

69.67

MTEB Code

68.76

Release Date

September 24, 2025

Strengths

  • SOTA on MTEB for sub-500M models
  • Comparable to models double its size
  • Robust to quantization
  • Ideal for on-device

Weaknesses

  • Embedding-only
  • Google usage license
  • Text-only

Competitor Comparison

Model
NV-Embed-v2
GritLM-7B

EmbeddingGemma is Google DeepMind's 308M parameter embedding model. SOTA on MTEB for sub-500M models.

Analysis generated: 2026-05-24