Gemma 3n E4B It Litert Preview GGUF

🚀 Gemma 3n Model

Gemma 3n is a lightweight, state - of - the - art open model from Google. It's designed for efficient execution on low - resource devices, capable of multimodal input and generating text outputs.

🚀 Quick Start

Model Usage Guidelines

• Currently, only text is supported.
• For Ollama, use the command: ollama run hf.co/unsloth/gemma-3n-E4B-it:Q4_K_XL. This will auto - set the correct chat template and settings.
• Set the following parameters: temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0.
• The maximum token limit (context length) for Gemma 3n is 32K. The chat template for Gemma 3n is as follows:

<bos><start_of_turn>user\nHello!<end_of_turn>\n<start_of_turn>model\nHey there!<end_of_turn>\n<start_of_turn>user\nWhat is 1+1?<end_of_turn>\n<start_of_turn>model\n

• For complete detailed instructions, refer to our step - by - step guide.

Fine - tuning Gemma 3n

• You can fine - tune Gemma 3n (4B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get - started/unsloth - notebooks).
• Read our Blog about Gemma 3n support: unsloth.ai/blog/gemma-3n.
• View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get - started/unsloth - notebooks).

⚠️ Important Note

Updated from google/gemma - 3n - E4B - it

💡 Usage Tip

• Learn how to run & fine - tune Gemma 3n correctly - Read our Guide.
• See our collection for all versions of Gemma 3n including GGUF, 4 - bit & 16 - bit formats.
• Unsloth Dynamic 2.0 achieves SOTA accuracy & performance versus other quants.

✨ Features

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, Gemma 3n models are designed for efficient execution on low - resource devices. They support multimodal input (text, image, video, and audio) and can generate text outputs. The models use selective parameter activation technology to reduce resource requirements and were trained with data in over 140 spoken languages.

📦 Installation

First, install the Transformers library. Gemma 3n is supported starting from transformers 4.53.0.

$ pip install -U transformers

💻 Usage Examples

Basic Usage

Running with the pipeline API

from transformers import pipeline
import torch
pipe = pipeline(
    "image-text-to-text",
    model="google/gemma-3n-e4b-it",
    device="cuda",
    torch_dtype=torch.bfloat16,
)

With instruction - tuned models, you need to use chat templates to process inputs first and then pass it to the pipeline.

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    }
]
output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"][-1]["content"])
# Okay, let's take a look!
# Based on the image, the animal on the candy is a **turtle**.
# You can see the shell shape and the head and legs.

Running the model on a single GPU

from transformers import AutoProcessor, Gemma3nForConditionalGeneration
from PIL import Image
import requests
import torch
model_id = "google/gemma-3n-e4b-it"
model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
processor = AutoProcessor.from_pretrained(model_id)
messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
            {"type": "text", "text": "Describe this image in detail."}
        ]
    }
]
inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)
input_len = inputs["input_ids"].shape[-1]
with torch.inference_mode():
    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
    generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
# **Overall Impression:** The image is a close-up shot of a vibrant garden scene,
# focusing on a cluster of pink cosmos flowers and a busy bumblebee.
# It has a slightly soft, natural feel, likely captured in daylight.

📚 Documentation

Model Information

Description

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. Gemma 3n models are designed for efficient execution on low - resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre - trained and instruction - tuned variants. These models were trained with data in over 140 spoken languages.

Gemma 3n models use selective parameter activation technology to reduce resource requirements. This technique allows the models to operate at an effective size of 2B and 4B parameters, which is lower than the total number of parameters they contain. For more information on Gemma 3n's efficient parameter management technology, see the Gemma 3n page.

Inputs and outputs

• Input:
  • Text string, such as a question, a prompt, or a document to be summarized.
  • Images, normalized to 256x256, 512x512, or 768x768 resolution and encoded to 256 tokens each.
  • Audio data encoded to 6.25 tokens per second from a single channel.
  • Total input context of 32K tokens.
• Output:
  • Generated text in response to the input, such as an answer to a question, analysis of image content, or a summary of a document.
  • Total output length up to 32K tokens, subtracting the request input tokens.

Model Data

Training Dataset

These models were trained on a dataset that includes a wide variety of sources totalling approximately 11 trillion tokens. The knowledge cutoff date for the training data was June 2024. Here are the key components:

• Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. The training dataset includes content in over 140 languages.
• Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code and understand code - related questions.
• Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries.
• Images: A wide range of images enables the model to perform image analysis and visual data extraction tasks.
• Audio: A diverse set of sound samples enables the model to recognize speech, transcribe text from recordings, and identify information in audio data.

The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.

Data Preprocessing

Here are the key data cleaning and filtering methods applied to the training data:

• CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content.
• Sensitive Data Filtering: As part of making Gemma pre - trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets.
• Additional methods: Filtering based on content quality and safety in line with our policies.

Implementation Information

Hardware

Gemma was trained using [Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro - to - tpu) hardware (TPUv4p, TPUv5p and TPUv5e). Training generative models requires significant computational power. TPUs, designed specifically for matrix operations common in machine learning, offer several advantages in this domain:

• Performance: TPUs are specifically designed to handle the massive computations involved in training generative models. They can speed up training considerably compared to CPUs.
• Memory: TPUs often come with large amounts of high - bandwidth memory, allowing for the handling of large models and batch sizes during training. This can lead to better model quality.
• Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for handling the growing complexity of large foundation models. You can distribute training across multiple TPU devices for faster and more efficient processing.
• Cost - effectiveness: In many scenarios, TPUs can provide a more cost - effective solution for training large models compared to CPU - based infrastructure, especially when considering the time and resources saved due to faster training.

These advantages are aligned with [Google's commitments to operate sustainably](https://sustainability.google/operating - sustainably/).

Software

Training was done using [JAX](https://github.com/jax - ml/jax) and [ML Pathways](https://blog.google/technology/ai/introducing - pathways - next - generation - ai - architecture/). JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models. ML Pathways is Google's latest effort to build artificially intelligent systems capable of generalizing across multiple tasks. This is specially suitable for foundation models, including large language models like these ones.

Together, JAX and ML Pathways are used as described in the paper about the Gemini family of models: "the 'single controller' programming model of Jax and Pathways allows a single Python process to orchestrate the entire training run, dramatically simplifying the development workflow."

Evaluation

Benchmark Results

These models were evaluated at full precision (float32) against a large collection of different datasets and metrics to cover different aspects of content generation. Evaluation results marked with IT are for instruction - tuned models. Evaluation results marked with PT are for pre - trained models.

Reasoning and factuality

[naturalq]: https://github.com/google - research - datasets/natural - questions [arc]: https://arxiv.org/abs/1911.01547 [winogrande]: https://arxiv.org/abs/1907.10641 [bbh]: https://paperswithcode.com/dataset/bbh [drop]: https://arxiv.org/abs/1903.00161

Multilingual

[global - mmlu]: https://huggingface.co/datasets/CohereLabs/Global - MMLU [eclektic]: https://arxiv.org/abs/2502.21228

STEM and code

[aime - 2025]: https://www.vals.ai/benchmarks/aime - 2025 - 05 - 09

Additional benchmarks

[global - mmlu - lite]: https://huggingface.co/datasets/CohereForAI/Global - MMLU - Lite

Ethics and Safety

Evaluation Approach

Our evaluation methods include structured evaluations and internal red - teaming testing of relevant content policies. Red - teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:

• Child Safety: Evaluation of text - to - text and image to text prompts covering child safety policies, including child sexual abuse and exploitation.
• Content Safety: Evaluation of text - to - text and image to text prompts covering safety policies including, harassment, violence and gore, and hate speech.
• Representational Harms: Evaluation of text - to - text and image to text prompts covering safety policies including bias, stereotyping, and harmful associations or inaccuracies.

In addition to development level evaluations, we conduct "assurance evaluations" which are our 'arms - length' internal evaluations for responsibility governance decision making. They are conducted separately from the model development team, to inform decision - making.

🔧 Technical Details

• Model Page: Gemma 3n
• Resources and Technical Documentation:
  • Responsible Generative AI Toolkit
  • Gemma on Kaggle
  • Gemma on HuggingFace
  • [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex - ai/publishers/google/model - garden/gemma3n)
• Terms of Use: Terms
• Authors: Google DeepMind

Citation

@article{gemma_3n_2025,
    title={Gemma 3n},
    url={https://ai.google.dev/gemma/docs/gemma-3n},
    publisher={Google DeepMind},
    author={Gemma Team},
    year={2025}
}

📄 License

The license for this model is gemma.