Gemma 3 1b It Llamafile

🚀 Gemma 3 1B Instruct - llamafile

Mozilla packaged the Gemma 3 models into executable weights (llamafiles), providing an easy and fast way to use the model across multiple operating systems.

🚀 Quick Start

To get started, you need both the Gemma 3 weights and the llamafile software. Both are included in a single file, which can be downloaded and run as follows:

wget https://huggingface.co/Mozilla/gemma-3-1b-it-llamafile/resolve/main/google_gemma-3-1b-it-Q6_K.llamafile
chmod +x google_gemma-3-1b-it-Q6_K.llamafile
./google_gemma-3-1b-it-Q6_K.llamafile

The default mode of operation for these llamafiles is the new command line chatbot interface.

✨ Features

• Cross - platform Compatibility: Works on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD systems (both AMD64 and ARM64).
• Multiple Usage Modes: Command - line chatbot, web GUI, and advanced CLI mode for shell scripting.
• Large Context Window: Supports a max context window size of 128k tokens.
• GPU Acceleration: Can utilize NVIDIA or AMD GPUs with sufficient RAM.

💻 Usage Examples

Basic Usage

You can use triple quotes to ask questions on multiple lines. You can pass commands like /stats and /context to see runtime status information. You can change the system prompt by passing the -p "new system prompt" flag. You can press CTRL - C to interrupt the model, and CTRL - D to exit.

./google_gemma-3-1b-it-Q6_K.llamafile

Advanced Usage

Web GUI

If you prefer to use a web GUI, then a --server mode is provided, that will open a tab with a chatbot and completion interface in your browser. For additional help on how it may be used, pass the --help flag. The server also has an OpenAI API compatible completions endpoint that can be accessed via Python using the openai pip package.

./google_gemma-3-1b-it-Q6_K.llamafile --server

Advanced CLI for Shell Scripting

An advanced CLI mode is provided that's useful for shell scripting. You can use it by passing the --cli flag. For additional help on how it may be used, pass the --help flag.

./google_gemma-3-1b-it-Q6_K.llamafile --cli -p 'four score and seven' --log-disable

📚 Documentation

Model Information

• Model Page: Gemma
• Model Creator: Google
• Original Model: google/gemma-3-1b-it

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 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre - trained variants and instruction - tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well - suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state - of - the - art AI models and helping foster innovation for everyone.

Inputs and Outputs

Usage Code Snippets

First, install the Transformers library. Gemma 3 is supported starting from transformers 4.50.0.

$ pip install -U transformers

Running with the pipeline API

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

from transformers import pipeline

pipe = pipeline("text-generation", model="google/gemma-3-1b-it", device="cuda", torch_dtype=torch.bfloat16)

messages = [
    [
        {
            "role": "system",
            "content": [{"type": "text", "text": "You are a helpful assistant."},]
        },
        {
            "role": "user",
            "content": [{"type": "text", "text": "Write a poem on Hugging Face, the company"},]
        },
    ],
]

output = pipe(messages, max_new_tokens=50)

Running the model on a single / multi GPU

from transformers import AutoTokenizer, BitsAndBytesConfig, Gemma3ForCausalLM
import torch

model_id = "google/gemma-3-1b-it"

quantization_config = BitsAndBytesConfig(load_in_8bit=True)

model = Gemma3ForCausalLM.from_pretrained(
    model_id, quantization_config=quantization_config
).eval()

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    [
        {
            "role": "system",
            "content": [{"type": "text", "text": "You are a helpful assistant."},]
        },
        {
            "role": "user",
            "content": [{"type": "text", "text": "Write a poem on Hugging Face, the company"},]
        },
    ],
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device).to(torch.bfloat16)


with torch.inference_mode():
    outputs = model.generate(**inputs, max_new_tokens=64)

outputs = tokenizer.batch_decode(outputs)

Citation

@article{gemma_2025,
    title={Gemma 3},
    url={https://goo.gle/Gemma3Report},
    publisher={Kaggle},
    author={Gemma Team},
    year={2025}
}

Model Data

Training Dataset

These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. 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.

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][safety - policies].

Implementation Information

Hardware

Gemma was trained using [Tensor Processing Unit (TPU)][tpu] hardware (TPUv4p, TPUv5p and TPUv5e). Training vision - language models (VLMS) 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 VLMs. 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][sustainability].

Software

Training was done using [JAX][jax] and [ML Pathways][ml - pathways]. 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][gemini - 2 - paper]; "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 against a large collection of different datasets and metrics to cover different aspects of text generation:

Reasoning and factuality

STEM and code

Multilingual

Multimodal

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... (The content seems incomplete here in the original, but we keep it as is)

🔧 Technical Details

Context Window

This model has a max context window size of 128k tokens. By default, a context window size of 8192 tokens is used. You can ask llamafile to use the maximum context size by passing the -c 0 flag. That's big enough for a small book. If you want to be able to have a conversation with your book, you can use the -f book.txt flag.

GPU Acceleration

On GPUs with sufficient RAM, the -ngl 999 flag may be passed to use the system's NVIDIA or AMD GPU(s). On Windows, only the graphics card driver needs to be installed if you own an NVIDIA GPU. On Windows, if you have an AMD GPU, you should install the ROCm SDK v6.1 and then pass the flags --recompile --gpu amd the first time you run your llamafile. On NVIDIA GPUs, by default, the prebuilt tinyBLAS library is used to perform matrix multiplications. This is open source software, but it doesn't go as fast as closed source cuBLAS. If you have the CUDA SDK installed on your system, then you can pass the --recompile flag to build a GGML CUDA library just for your system that uses cuBLAS. This ensures you get maximum performance.

📄 License

• License: gemma
• License Link: LICENSE

⚠️ Troubleshooting

Common Issues

• Run - detector errors on Linux: On Linux, the way to avoid run - detector errors is to install the APE interpreter.

sudo wget -O /usr/bin/ape https://cosmo.zip/pub/cosmos/bin/ape-$(uname -m).elf
sudo chmod +x /usr/bin/ape
sudo sh -c "echo ':APE:M::MZqFpD::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"
sudo sh -c "echo ':APE-jart:M::jartsr::/usr/bin/ape:' >/proc/sys/fs/binfmt_misc/register"

• Windows 4GB limit: On Windows there's a 4GB limit on executable sizes.

For more issues, see the "Gotchas" section of the README.