Post-Cutoff

Google DeepMindGemma familyCurrentEmbedding modelReleased 6 Oct 2026

EmbeddingGemma 2

Small open on-device embedding model for multimodal search, RAG, classification and clustering.

Model idgoogle/embeddinggemma-2

PricePrice not published

Checked7 October 2026

Where it stands

No newer embedding model in our registry yet.

All embedding models

Before it from Google
Gemini Embedding 222 Apr 2026
Weights
Weights are public under a permissive licence (Apache-2.0).

How to call it

2 ways to use EmbeddingGemma 2, with the model id each provider expects.

Providers, model ids, endpoints and docs for EmbeddingGemma 2
ProviderModel idEndpointDocs
Hugging Face google/embeddinggemma-2 huggingface.co
Google docs ai.google.dev

Pricing

Price not published.

No price source linked. Checked 7 October 2026.

Specs

Input
Text, images, video and audio
Output
Text
Context window
8,192 tokens
Max output
Not published
Open weights
Yes
Licence
Apache-2.0
Released
6 October 2026
Status
Current
Type
Embedding model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Four modalities in one small open embedding space

    Maps text (including code), images, video and audio into one 768-dimensional space with 740M parameters in total: a 270M text model (130M backbone + 140M embedder) plus optional 170M vision and 300M audio encoders that can be loaded separately.

    Source: huggingface.co

  • Matryoshka truncation

    Embeddings can be cut to 512, 256 or 128 dimensions (up to 6x less storage); quality loss is small down to 256d.

    Source: huggingface.co

  • Big code-retrieval gain over v1

    MTEB code v1 78.68 vs 68.76 for EmbeddingGemma 1; MTEB multilingual v2 61.36 vs 61.15; MMEB v2 overall 59.01 (Google’s numbers).

    Source: huggingface.co

Notes

Announced 2026-10-06 on the Google blog. Apache 2.0 (Gemma 4 license), not gated on Hugging Face. Runs on phones and laptops; uses task-instruction prefixes (e.g. ‘task: search result | query: ...’) for text inputs. sentence-transformers id: google/embeddinggemma-2. No hosted Gemini API endpoint is listed; for hosted multimodal embeddings Google offers gemini-embedding-2.

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("google/embeddinggemma-2")
q = model.encode("What causes the northern lights?", prompt_name="SearchQuery")
d = model.encode("The northern lights are caused by charged particles from the sun.", prompt_name="Document")
print(model.similarity(q, d))

Sources: Hugging Face model card, launch blog, docs.