Search and RAG

EmbeddingGemma

A small multilingual embedding model based on Gemma 3 that runs even on a phone or laptop without internet.

Developer
Google, USA
First release
Sep 2025
Latest release
Sep 2025
Sizes
300M
License
Commercial use with conditionsGemma Terms of Use (Google's own license, commercial use allowed with usage rules)
Russian
Not stated
Ready-made builds
GGUF, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting
Deploy on your server Hugging Face

What it does

  • On-device document search
  • RAG without sending data outside
  • Text classification

Where it is used

Mobile appsWork with sensitive dataSmall businesses

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. EmbeddingGemma 300M

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can EmbeddingGemma be used in a commercial project?

With conditions. License: Gemma Terms of Use (Google's own license, commercial use allowed with usage rules). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does EmbeddingGemma need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does EmbeddingGemma support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download EmbeddingGemma and what does it cost?

The EmbeddingGemma weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextGemmaGoogle · USACommercial use allowed

Compact Google models that run well on a single computer; larger versions understand images. Includes CodeGemma for code, FunctionGemma 270M for function calling and the fast DiffusionGemma.

DetailsSearch and RAGE5 / multilingual-e5Microsoft · USACommercial use allowed

Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.

DetailsSearch and RAGGranite EmbeddingIBM · USACommercial use allowed

Lightweight IBM embeddings for enterprise search, trained on data with clear rights. R2, released in 2026, became multilingual.

Details

Source: huggingface.co/google/embeddinggemma-300m. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.