Skip to content

EmbeddingGemma 2

Hugging Face (open weights) Open weights

The catch: A fixed 768-dimension vector space, and 8K tokens of input shared across all media in one item.

AccessOpen weights
Free limitsFree to download and self-host; you pay only for your own compute. 740M multimodal embedding model: text (including code), images, video and audio into one 768-dimension space; 8,192-token input. Released 14 Sep 2026; not gated, unlike EmbeddingGemma 300M.
Modalityembeddings
Credit cardNot required
Commercial useAllowed
Trains on your data–
Licence or termsApache-2.0
Context window8,192 tokens
Model idgoogle/embeddinggemma-2
Base URL–
Last checked8 Oct 2026

How to use EmbeddingGemma 2

Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.

Quickstart
pip install -U sentence-transformers transformers && python -c "from sentence_transformers import SentenceTransformer; print(SentenceTransformer('google/embeddinggemma-2').encode(['hello']).shape)"
Paste into Claude Code
I want to run the open-weight model "EmbeddingGemma 2" (google/embeddinggemma-2) for my project.
Please:
1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint).
2. Give me a minimal working setup and a test request.
3. Tell me the licence terms for commercial use.
4. If a cheaper or smaller variant would do the job, mention it.

Before you ship on it

  • A fixed 768-dimension vector space, and 8K tokens of input shared across all media in one item.
  • Apache-2.0 (licence tag on the HF repo): use, modify, distribute and sell, including commercially; keep the licence and notices when you redistribute.
  • Free to run means you pay for the GPUs, the serving stack and the on-call.

Questions

Is EmbeddingGemma 2 free?

Yes. Open weights offers it as open weights, with these limits: Self-host free · Apache-2.0. No credit card is needed.

Can I use EmbeddingGemma 2 commercially?

Yes, under Apache-2.0. Check the current terms before you ship.

How do I start with EmbeddingGemma 2?

Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.

Source: huggingface.co/google/embeddinggemma-2, checked 8 Oct 2026.