Skip to main content
Local LLM Guide

Model

EmbeddingGemma 300M

Use it in a supported document-search workflow. It does not generate chat answers. Memory requirement not supplied; check the model and app instructions. Best use: Private offline search, mobile document search, and simple document lookup on laptops without dedicated GPUs locally.

0.308BEmbedding

Best use

Private offline search, mobile document search, and simple document lookup on laptops without dedicated GPUs locally.

Memory planning

Memory requirement not supplied; check the model and app instructions

Expected pace

Depends on your hardware, app, and conversation length

License

Gemma; read the model’s terms before use

Who should use this model?

  • Private offline search, mobile document search, and simple document lookup on laptops without dedicated GPUs locally.

Choose something else when

  • Your documents exceed 2K tokens per chunk, or you need multimodal retrieval support today locally.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. Document-search memory also depends on input length, batch size, and the document index; a chat-memory estimate does not confirm that workload.

CPU only
Memory or response time may limit use. Try a smaller model first.
8GB system memory
Memory or response time may limit use. Try a smaller model first.
16GB system memory
Memory or response time may limit use. Try a smaller model first.
32GB system memory
Memory or response time may limit use. Try a smaller model first.
8GB GPU memory
Memory or response time may limit use. Try a smaller model first.
12GB GPU memory
Memory or response time may limit use. Try a smaller model first.
24GB GPU memory
Memory or response time may limit use. Try a smaller model first.
Apple unified memory
Memory or response time may limit use. Try a smaller model first.

Model facts that change the decision

Parameters
0.308B
Input
Text
Published context limit
2,048 tokens
Model format
safetensors · GGUF · Ollama · sentence-transformers · TEI
Languages
100+ languages

Using this model for document search

Select this model for the document-search step in an app that supports it. Keep the model that generates answers separate. Check document chunk length and any required query or document prefixes in the model’s instructions.

Changing the embedding model changes the document vectors. Rebuild the document index rather than mixing vectors from different models.

First setup

Download with Ollama

ollama pull embeddinggemma

LM Studio: Check that your installed app supports the exact model format and task before downloading it.

llama.cpp

Use a cited GGUF build with current llama.cpp-compatible tooling.

Conditions that change the answer

  • Google documentation uses 308M parameters, while some catalog surfaces use the 300M label.
  • The context window is 2K tokens, so long documents should be chunked carefully.
  • The model uses the Gemma license, not Apache-2.0; users must accept and comply with Google terms.
  • Google states sub-200MB RAM with quantization, but exact Q4, Q5, and Q8 file sizes were not specified here.
  • Commercial use: Allowed under Gemma license and Google terms; responsible commercial use is permitted with prohibited-use restrictions.
  • EmbeddingGemma is Google’s small text embedding model for private local search. It turns notes, documents, or app text into vectors on laptops and mobile-class devices, making offline document search practical without heavy GPU hardware for beginners.

Read the controlling license text →