You can deploy this model and start earning money today!

bmabir17/
embeddinggemma-300m

Name: embeddinggemma-300m
Availability: InStock

sentence-transformers

tflite

sentence-similarity

feature-extraction

text-embeddings-inference

gemma

endpoints_compatible

Views

No views yet

litert-community/embeddinggemma-300m

Main Model Card: google/embeddinggemma-300m

Overview

This model card provides a few variants of the EmbeddingGemma model that are ready for deployment on Android and iOS using LiteRT, or on Android via the Google AI Edge RAG Library.

Use the models

LiteRT

Try out the demo example on GitHub.

RAG

Try out the EmbeddingGemma model in the in the Google AI Edge RAG Library. You can find the SDK on GitHub or follow our Android guide to install directly from Maven. We have also published a sample app.
Use the sentencepiece model as the tokenizer for the EmbeddingGemma model.

Performance

Android

Note that all benchmark stats are from a Samsung S25 Ultra.

Backend	Quantization	Max sequence length	Init time (ms)	Inference time (ms)	Memory (RSS in MB)	Model size (MB)
NPU	Mixed Precision*	256	206	7.8	224	182
NPU	Mixed Precision*	512	241	18	231	184
NPU	Mixed Precision*	1024	272	57	263	195
NPU	Mixed Precision*	2048	468	169	332	220
GPU	Mixed Precision*	256	1175	64	762	179
GPU	Mixed Precision*	512	1445	119	762	179
GPU	Mixed Precision*	1024	1545	241	771	183
GPU	Mixed Precision*	2048	1707	683	786	196
CPU	Mixed Precision*	256	17.6	66	110	179
CPU	Mixed Precision*	512	24.9	169	123	179
CPU	Mixed Precision*	1024	35.4	549	169	183
CPU	Mixed Precision*	2048	35.8	2455	333	196

*Mixed Precision refers to per-channel quantization with int4 for embeddings, feedforward, and projection layers, and int8 for attention (e4_a8_f4_p4).

Notes:

Init time: the cost paid once per application initialization – subsequent inferences do not pay this cost
Memory: indicator of peak RAM usage
Model Size: measured by the size of the .tflite flatbuffer (serialization format for LiteRT models)
The inference on CPU is accelerated via the LiteRT XNNPACK delegate with 4 threads
Benchmark is run with cache enabled and initialized. During the first run, the latency may differ.

Google Tensor Compilation Guide

To compile for Google Tensor hardware, please follow the step-by-step instructions available in the Google Tensor Official User Guide.

For detailed Google Tensor Compiler configuration, refer to the Install Google Tensor SDK section within the LiteRT_AOT_Compilation_Tutorial.ipynb notebook.

Please note that the embedding-gemma models were compiled using standard configurations; no additional compilation flags are required.

bmabir17/embeddinggemma-300m