EmbeddingGemma 2
Google DeepMind · · 6 days after Gemini 4 Argon
Partially verified
0 of 2 published values traced to a source1 primary source, 1 archived2 not disclosed by the lab
Why this status
Cited to the lab's own announcement. Not verified because the release date and the parameter count could not be found in any cited primary source — the value may be correct, but this dataset cannot yet show where it came from. Modalities recorded as text-to-text. The primary source states the model is text-only. Capabilities evidenced from the primary sources: video: “6, 2026 Google AI Edge Team Android ML Team Share Facebook Twitter LinkedIn Mail Today, Google DeepMind launched EmbeddingGemma 2 , a best-in-class for its size, open-weight, multi”.
What these states mean · How records are judged · Has this record changed?
Google's open-weights multimodal embedding model: 740M parameters mapping text, images, video frames and audio into one vector space, built to run on device. A text-only subset loads alone.
Details
| Released | October 6, 2026 |
|---|---|
| Company | Google DeepMind |
| Family | Gemma |
| Era | Agentic systems |
| Type | Language model · Embedding model |
| Modalities | Text → Text |
| Capabilities | Video |
| Weights | Open weights |
| Licence | Not disclosed |
| Context window | Not disclosed |
| Parameters | 740M |
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
- Weights and model card Hugging Face ↗
Sources
Record status: partly verified · confidence 60/100 · 1 of 1 primary
Cited to the lab's own announcement. Not verified because the release date and the parameter count could not be found in any cited primary source — the value may be correct, but this dataset cannot yet show where it came from. Modalities recorded as text-to-text. The primary source states the model is text-only. Capabilities evidenced from the primary sources: video: “6, 2026 Google AI Edge Team Android ML Team Share Facebook Twitter LinkedIn Mail Today, Google DeepMind launched EmbeddingGemma 2 , a best-in-class for its size, open-weight, multi”.
- developers.googleblog.com Official announcement archived
Primary means published by the organisation that made the model. Verified records require at least one.
Gemma family
- Gemma February 21, 2024
- Gemma 3 March 12, 2025
- Gemma 4 12B June 3, 2026
- EmbeddingGemma 2 October 6, 2026
Compare EmbeddingGemma 2 with another model →
See EmbeddingGemma 2 on the interactive timeline →