gemma-3-27b-it
PREVIEWCutting-edge open multimodal model exceling in high-quality reasoning from images.
Gemma 3 model
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. This model is ready for commercial use.
Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA Gemma 3 model card.
License/Terms of Use
GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the NVIDIA Community Model License. ADDITIONAL INFORMATION: Gemma Terms of Use.
Deployment Geography
Global
Use Case
Models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning.
Benefits
At the time of release, this family of models provides high-performance open vision-language model implementations designed from the ground up for responsible AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives.
Release Date
- Build.Nvidia.com - 3/11/2025 via https://build.nvidia.com/google/gemma-3-1b-it and https://build.nvidia.com/google/gemma-3-27b-it
References
Model Page: Gemma Authors: Google DeepMind
- Gemma 3 Technical Report
- Responsible Generative AI Toolkit
- Gemma on Kaggle
- Gemma on Vertex Model Garden
Model Architecture
Architecture Type: Dense decoder-only Transformer model
Inputs and outputs
Input
Input Type(s): Text, Text+Image
Input Format(s):
- String
- Image: jpg
Input Parameters:
- Text: One-dimensional (1D)
- Image: Two-dimensional (2D)
Other Properties Related to Input:
- Text string, such as a question, a prompt, or a document to be summarized
- Images, normalized to 896 x 896 resolution and encoded to 256 tokens each
- Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and 32K tokens for the 1B size
Output
Output Type(s): Text
Output Format: String
Output Parameters: (1D)
Other Properties Related to 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 context of 8192 tokens
Software Integration
Runtime Engine(s): TRT-LLM
Supported Hardware Microarchitecture Compatibility: NVIDIA Ampere, NVIDIA Blackwell, NVIDIA Jetson, NVIDIA Hopper, NVIDIA Lovelace, NVIDIA Pascal, NVIDIA Turing, and NVIDIA Volta architectures
[Preferred/Supported] Operating System(s): Linux
Model Version(s):
- Gemma 3 IT 1B: 1.0 (3/12/2025)
- Gemma 3 IT 4B: 1.0 (3/12/2025)
- Gemma 3 IT 12B: 1.0 (3/12/2025)
- Gemma 3 IT 27B: 1.0 (3/12/2025)
Software
Training was done using JAX and 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 especially 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."
Training, Testing, and Evaluation Datasets
Training Dataset
Data Collection Method by dataset: Hybrid: Human, Automated
Labeling Method by dataset: Hybrid: Human, Automated
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 address mathematical queries.
- Images: A wide range of images enables the model to perform image analysis and visual data extraction tasks.
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 Google Responsible AI policies.
Testing Dataset
Data Collection Method by dataset: Hybrid: Human, Automated
Labeling Method by dataset: Hybrid: Human, Automated
Evaluation Dataset
Data Collection Method by dataset: Hybrid: Human, Automated
Labeling Method by dataset: Hybrid: Human, Automated
Evaluation
Model evaluation metrics and results are highlighted below.
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
| Benchmark | Metric | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|---|---|---|---|---|---|
| HellaSwag | 10-shot | 62.3 | 77.2 | 84.2 | 85.6 |
| BoolQ | 0-shot | 63.2 | 72.3 | 78.8 | 82.4 |
| PIQA | 0-shot | 73.8 | 79.6 | 81.8 | 83.3 |
| SocialIQA | 0-shot | 48.9 | 51.9 | 53.4 | 54.9 |
| TriviaQA | 5-shot | 39.8 | 65.8 | 78.2 | 85.5 |
| Natural Questions | 5-shot | 9.48 | 20.0 | 31.4 | 36.1 |
| ARC-c | 25-shot | 38.4 | 56.2 | 68.9 | 70.6 |
| ARC-e | 0-shot | 73.0 | 82.4 | 88.3 | 89.0 |
| WinoGrande | 5-shot | 58.2 | 64.7 | 74.3 | 78.8 |
| BIG-Bench Hard | few-shot | 28.4 | 50.9 | 72.6 | 77.7 |
| DROP | 1-shot | 42.4 | 60.1 | 72.2 | 77.2 |
STEM and code
| Benchmark | Metric | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|---|---|---|---|---|
| MMLU | 5-shot | 59.6 | 74.5 | 78.6 |
| MMLU (Pro COT) | 5-shot | 29.2 | 45.3 | 52.2 |
| AGIEval | 3-5-shot | 42.1 | 57.4 | 66.2 |
| MATH | 4-shot | 24.2 | 43.3 | 50.0 |
| GSM8K | 8-shot | 38.4 | 71.0 | 82.6 |
| GPQA | 5-shot | 15.0 | 25.4 | 24.3 |
| MBPP | 3-shot | 46.0 | 60.4 | 65.6 |
| HumanEval | 0-shot | 36.0 | 45.7 | 48.8 |
Multilingual
| Benchmark | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|---|---|---|---|---|
| MGSM | 2.04 | 34.7 | 64.3 | 74.3 |
| Global-MMLU-Lite | 24.9 | 57.0 | 69.4 | 75.7 |
| WMT24++ (ChrF) | 36.7 | 48.4 | 53.9 | 55.7 |
| FloRes | 29.5 | 39.2 | 46.0 | 48.8 |
| XQuAD (all) | 43.9 | 68.0 | 74.5 | 76.8 |
| ECLeKTic | 4.69 | 11.0 | 17.2 | 24.4 |
| IndicGenBench | 41.4 | 57.2 | 61.7 | 63.4 |
Multimodal
| Benchmark | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|---|---|---|---|
| COCOcap | 102 | 111 | 116 |
| DocVQA (val) | 72.8 | 82.3 | 85.6 |
| InfoVQA (val) | 44.1 | 54.8 | 59.4 |
| MMMU (pt) | 39.2 | 50.3 | 56.1 |
| TextVQA (val) | 58.9 | 66.5 | 68.6 |
| RealWorldQA | 45.5 | 52.2 | 53.9 |
| ReMI | 27.3 | 38.5 | 44.8 |
| AI2D | 63.2 | 75.2 | 79.0 |
| ChartQA | 63.6 | 74.7 | 76.3 |
| VQAv2 | 63.9 | 71.2 | 72.9 |
| BLINK | 38.0 | 35.9 | 39.6 |
| OKVQA | 51.0 | 58.7 | 60.2 |
| TallyQA | 42.5 | 51.8 | 54.3 |
| SpatialSense VQA | 50.9 | 60.0 | 59.4 |
| CountBenchQA | 26.1 | 17.8 | 68.0 |
Inference
Engine: Transformers
Test Hardware: NVIDIA Hopper
Ethics and Safety
Ethics and safety evaluation approach and results are highlighted below.
Evaluation Approach
The evaluation method included 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, assurance evaluations were conducted using the "arms-length" internal evaluations for responsibility governance decision making. They are conducted separately from the model development team, to inform decision making about release. High level findings are fed back to the model team, but prompt sets are held-out to prevent overfitting and preserve the results' ability to inform decision making. Assurance evaluation results are reported to the Responsibility & Safety Council as part of release review.
Evaluation Results
For all areas of safety testing, there were major improvements in the categories of child safety, content safety, and representational harms relative to previous Gemma models. All testing was conducted without safety filters to evaluate the model capabilities and behaviors. For both text-to-text and image-to-text, and across all model sizes, the model produced minimal policy violations, and showed significant improvements over previous Gemma models' performance with respect to ungrounded inferences. One limitation of the evaluation was that the models incorporated only English language prompts.
Usage and Limitations
The potential limitations for these models are outlined below.
Intended Usage
Open vision-language models (VLMs) models have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.
- Content Creation and Communication
- Text Generation: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts.
- Chatbots and Conversational AI: Power conversational interfaces for customer service, virtual assistants, or interactive applications.
- Text Summarization: Generate concise summaries of a text corpus, research papers, or reports.
- Image Data Extraction: These models can be used to extract, interpret, and summarize visual data for text communications.
- Research and Education
- Natural Language Processing (NLP) and VLM Research: These models can serve as a foundation for researchers to experiment with VLM and NLP techniques, develop algorithms, and contribute to the advancement of the field.
- Language Learning Tools: Support interactive language learning experiences, aiding in grammar correction or providing writing practice.
- Knowledge Exploration: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics.
Model Limitations
- Training Data
- The quality and diversity of the training data significantly influence the model's capabilities. Biases or gaps in the training data can lead to limitations in the model's responses.
- The scope of the training dataset determines the subject areas the model can handle effectively.
- Context and Task Complexity
- Models are better at tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging.
- A model's performance can be influenced by the amount of context provided (longer context generally leads to better outputs, up to a certain point).
- Language Ambiguity and Nuance
- Natural language is inherently complex. Models might struggle to grasp subtle nuances, sarcasm, or figurative language.
- Factual Accuracy
- Models generate responses based on information they learned from their training datasets, but they are not knowledge bases. They may generate incorrect or outdated factual statements.
- Common Sense
- Models rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations.
Identified risks and mitigations
- Perpetuation of biases: It's encouraged to perform continuous monitoring (using evaluation metrics, human review) and the exploration of de-biasing techniques during model training, fine-tuning, and other use cases.
- Generation of harmful content: Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards based on their specific product policies and application use cases.
- Misuse for malicious purposes: Technical limitations and developer and end-user education can help mitigate against malicious applications of VLMs. Educational resources and reporting mechanisms for users to flag misuse are provided. Prohibited uses of Gemma models are outlined in the Gemma Prohibited Use Policy.
- Privacy violations: Models were trained on data filtered for removal of certain personal information and other sensitive data. Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques.
Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report security vulnerabilities or NVIDIA AI Concerns here.