gemma Documentation

Index Copy Section

.. toctree::
    :hidden:
    :caption: Guides

    colab_sampling
    colab_multimodal
    colab_finetuning
    colab_tool_use
    colab_sharding
    colab_tokenizer
    colab_lora_sampling
    colab_lora_finetuning
    peft
    checkpoints
    research

.. toctree::
    :hidden:
    :caption: Links

    GitHub <https://github.com/google-deepmind/gemma>
    Issues <https://github.com/google-deepmind/gemma/issues>
    Ecosystem <https://ai.google.dev/gemma>

.. toctree::
    :hidden:
    :caption: API

    api/gm/index
    api/peft/index

Checkpoints Copy Section

Checkpoints

Kaggle Hub Copy Chapter

Gemma models are available on Kaggle Hub for various formats:

• Gemma 4
• Gemma 3
• Gemma 2
• Gemma 1

To manually download the model:

• Select one of the Flax model variations
• Click the "Download" button to download the model archive
• Extract the model files from the archive

The archive contains both the model weights and the tokenizer, like:

2b/              # Directory containing model weights
tokenizer.model  # Tokenizer

To programmatically download the model:

import kagglehub

kagglehub.login()

weights_dir = kagglehub.model_download(f'google/gemma-3/flax/gemma3-4b-it')

v4 Copy Section

NOTE: Gemma 4 Flax checkpoints will be updated on Kaggle when possible.

Research Copy Section

Research

Custom transformer Copy Chapter

For experimentation, you might want to create smaller custom versions of
Transformer, rather than using the default official "Gemma" pre-trained ones.

Here is an example to create a text-only, 12 layers transformer:

class MyTinyTransformer(gm.nn.Transformer):
  config: gm.nn.config.TransformerConfig = gm.nn.config.TransformerConfig(
      final_logit_softcap=None,
      num_embed=262144,  # Vocab size, matching the tokenizer
      embed_dim=896,
      hidden_dim=4 * 896,
      num_heads=4,
      head_dim=256,
      num_kv_heads=1,
      use_post_attn_norm=True,
      use_post_ffw_norm=True,
      use_qk_norm=True,
      attention_types=gm.nn.config.make_attention_layers_types(
          pattern=gm.nn.config.GEMMA3_ATTENTION_PATTERN,
          num_layers=12,
      ),
      query_pre_attn_norm=gm.nn.config.QueryPreAttentionNormalisation.BY_ONE_OVER_SQRT_HEAD_DIM,
      attn_logits_soft_cap=None,
      sliding_window_size=512,
      transpose_gating_einsum=True,
      local_base_frequency=10_000,
      global_base_frequency=1_000_000,
      vision_encoder=None,  # Text-only
  )

  INFO = gm.nn.config.ModelInfo(
      tokenizer_version=3,  # Auto-select the tokenizer in the sampler
  )

Gemma-related projects Copy Chapter

The Gemma repository also contain various non-official research projects around
Gemma, located in the research/
directory:

• t5gemma:
  Encoder/decoder Gemma architecture, based on Gemma 2.

CHANGELOG Copy Section

Changelog

[Unreleased] Copy Chapter

[4.1.0] - 2026-06-11 Copy Chapter

• Release Diffusion Gemma

[4.0.1] - 2026-05-20 Copy Chapter

• Fix dialog dependency requirement to be >= 1.1.0.

[4.0.0] - 2026-04-17 Copy Chapter

• Add Gemma 4.

[1.0.0] - 2022-01-01 Copy Chapter

• Initial release

CONTRIBUTING Copy Section

How to Contribute

We would love to accept your patches and contributions to this project.

Before you begin Copy Chapter

Sign our Contributor License Agreement Copy Section

Contributions to this project must be accompanied by a
Contributor License Agreement (CLA).
You (or your employer) retain the copyright to your contribution; this simply
gives us permission to use and redistribute your contributions as part of the
project.

If you or your current employer have already signed the Google CLA (even if it
was for a different project), you probably don't need to do it again.

Visit https://cla.developers.google.com/ to see your current agreements or to
sign a new one.

Review our Community Guidelines Copy Section

This project follows Google's Open Source Community
Guidelines.

Contribution process Copy Chapter

Code Reviews Copy Section

All submissions, including submissions by project members, require review. We
use GitHub pull requests
for this purpose.

README Copy Section

Gemma

Gemma is a family of open-weights Large Language
Model (LLM) by Google DeepMind, based on Gemini
research and technology.

This repository contains the implementation of the
gemma PyPI package. A
JAX library to use and fine-tune Gemma.

For examples and use cases, see our
documentation. Please
report issues and feedback in
our GitHub.

Installation Copy Section

1. Install JAX for CPU, GPU or TPU. Follow the instructions on
   the JAX website.

2. Run

   sh Copy

   pip install gemma

Examples Copy Section

Here is a minimal example to have a multi-turn, multi-modal conversation with
Gemma:

from gemma import gm

# Model and parameters (Gemma 4)
model = gm.nn.Gemma4_E4B()
params = gm.ckpts.load_params(gm.ckpts.CheckpointPath.GEMMA4_E4B_IT)

# Example of multi-turn conversation
sampler = gm.text.ChatSampler(
    model=model,
    params=params,
    multi_turn=True,
)

prompt = """Which of the 2 images do you prefer ?

Image 1: <|image|>
Image 2: <|image|>

Write your answer as a poem."""
out0 = sampler.chat(prompt, images=[image1, image2])

out1 = sampler.chat('What about the other image ?')

The same ChatSampler API works with all Gemma versions (2, 3, 3n, 4).

Our documentation contains various Colabs and tutorials, including:

• Sampling
• Multi-modal
• Fine-tuning
• LoRA
• ...

Additionally, our
examples/ folder
contain additional scripts to fine-tune and sample with Gemma.

Learn more about Gemma Copy Section

• To use this library: Gemma documentation
• Technical reports for metrics and model capabilities:
  • Gemma 1
  • Gemma 2
  • Gemma 3
  • Gemma 4
• Other Gemma implementations and doc on the
  Gemma ecosystem

Downloading the models Copy Section

To download the model weights. See
our documentation.

System Requirements Copy Section

Gemma can run on a CPU, GPU and TPU. For GPU, we recommend 8GB+ RAM on GPU for
The 2B checkpoint and 24GB+ RAM on GPU are used for the 7B checkpoint.

Contributing Copy Section

We welcome contributions! Please read our Contributing Guidelines before submitting a pull request.

This is not an official Google product.