google/gemma-3-270m-it

TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Jul 30, 2025License:gemmaArchitecture:Transformer0.6K Gated Featherless Exclusive Cold

The google/gemma-3-270m-it is a 270 million parameter instruction-tuned multimodal model from Google DeepMind, part of the Gemma 3 family. It handles both text and image inputs, generating text outputs, and features a 32K token context window. This model is optimized for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning, and is designed for deployment in resource-constrained environments.

Loading preview...

Model Overview

Google DeepMind's Gemma 3 models are a family of lightweight, open multimodal models built using the same research and technology as the Gemini models. The gemma-3-270m-it is the smallest instruction-tuned variant, featuring 270 million parameters and a 32K token context window. It is capable of processing both text and image inputs (images normalized to 896x896 resolution, encoded to 256 tokens) and generating text outputs.

Key Capabilities

  • Multimodal Input: Processes text and image inputs for comprehensive understanding.
  • Text Generation: Excels at tasks like question answering, summarization, and reasoning.
  • Multilingual Support: Trained on data including over 140 languages.
  • Resource-Efficient: Its small size allows for deployment on devices with limited resources, such as laptops and desktops.
  • Robust Training: Trained on 6 trillion tokens with a knowledge cutoff of August 2024, incorporating web documents, code, mathematics, and images.

Intended Use Cases

This model is well-suited for a wide range of applications, including:

  • Content Creation: Generating creative text formats, marketing copy, and email drafts.
  • Conversational AI: Powering chatbots and virtual assistants.
  • Text Summarization: Creating concise summaries of documents and research papers.
  • Image Data Extraction: Interpreting and summarizing visual data for text communications.
  • Research & Education: Serving as a foundation for VLM and NLP research, and supporting language learning tools.