gemma-4-E2B-it-litert-lm

litert-community/gemma-4-E2B-it-litert-lm

Main Model Card: google/gemma-4-E2B-it

This model card provides the Gemma 4 E2B model in a way that is ready for deployment on Android, iOS, Desktop, IoT and Web.

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. This particular Gemma 4 model is small so it is ideal for on-device use cases. By running this model on device, users can have private access to Generative AI technology without even requiring an internet connection.

These models are provided in the .litertlm format for use with the LiteRT-LM framework. LiteRT-LM is a specialized orchestration layer built directly on top of LiteRT, Google’s high-performance multi-platform runtime trusted by millions of Android and edge developers. LiteRT provides the foundational hardware acceleration via XNNPack for CPU and ML Drift for GPU. LiteRT-LM adds the specialized GenAI libraries and APIs, such as KV-cache management, prompt templating, and function calling. This integrated stack is the same technology powering the Google AI Edge Gallery showcase app.

The model file size is 2.59 GB, which includes a text decoder with 0.79GB of weights and 1.12GB of embedding parameters. LiteRT-LM framework always keeps main weights in memory, while the embedding parameters are memory mapped which enables significant working memory savings on some platforms as seen in the detailed data below. The vision and audio models are loaded as needed to further reduce memory consumption.

Try Gemma 4 E2B

<div align="center"> </div>

Build with Gemma 4 E2B and LiteRT-LM

Ready to integrate this into your product? Get started here.

Gemma 4 E2B Performance on LiteRT-LM

All benchmarks were taken using 1024 prefill tokens and 256 decode tokens with a context length of 2048 tokens via LiteRT-LM. The model can support up to 32k context length. The inference on CPU is accelerated via the LiteRT XNNPACK delegate with 4 threads. Time-to-first-token does not include load time. Benchmarks were run with caches enabled and initialized. During the first run, the latency and memory usage may differ. Model size is the size of the file on disk.

CPU memory was measured using, rusage::ru_maxrss on Android, Linux and Raspberry Pi, task_vm_info::phys_footprint on iOS and MacBook and process_memory_counters::PrivateUsage on Windows.

Android

Note: On supported Android devices, Gemma 4 is available through Android AI Core as Gemini Nano, which is the recommended path for production applications.

🚨 NEW: Android with Speculative Decoding 🚨

The numbers in this section include speculative decoding. Speculative decoding is an optimization that accelerates LLMs by using a small, fast "draft" model to quickly predict multiple upcoming tokens, while a larger “target” model then verifies those tokens in parallel. The effectiveness of speculative decoding is task dependent because the “draft” model can more easily predict the correct tokens of some tasks. The metrics in this section were collected from a variety of sample prompts and grouped into categories by task type. The baseline measurements are an average across all task types. The number of input and output tokens varied across prompts. Note that if you download this model before May 5, 2026, you should re-download the model if you want to use speculative decoding. Speculative decoding is available on CPU and GPU on Mobile and Desktop.

iOS

Linux

macOS

Windows

IoT

<small>

• NPU model is benchmarked with 4096 context length

</small>

Gemma 4 E2B on Web

Running Gemma inference on the web is currently supported through LLM Inference Engine and uses the gemma-4-E2B-it-web.task model file. Try it out live in your browser (Chrome with WebGPU recommended). To start developing with it, download the web model and run with our sample web page, or follow the guide to add it to your own app.

Benchmarked in Chrome on a MacBook Pro 2024 (Apple M4 Max) with 1024 prefill tokens and 256 decode tokens, but the model can support context lengths up to 128K.

<small>

• GPU memory measured by "GPU Process" memory for all of Chrome while running. Was 130MB when inactive, before any model loading took place.
• CPU memory measured for the entire tab while running. Was 55MB when inactive, before any model loading took place.

</small>