ECE-Software/gemma-3-270m

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Oct 4, 2026License:gemmaArchitecture:Transformer Featherless Exclusive Cold

Gemma 3 270M is a 0.3 billion parameter multimodal open model developed by Google DeepMind, built from the same research and technology as the Gemini models. It handles text and image input, generating text output, and supports over 140 languages with a 32K token context window. This compact model is designed for text generation and image understanding tasks like question answering, summarization, and reasoning, making it suitable for deployment in resource-limited environments.

Loading preview...

Overview

Gemma 3 is a family of lightweight, state-of-the-art open models from Google DeepMind, leveraging the same research and technology as the Gemini models. The Gemma 3 270M variant is a compact 0.3 billion parameter model with a 32K token context window, designed for efficient deployment. It is multimodal, accepting both text and image inputs (images normalized to 896x896 resolution, encoded to 256 tokens each for larger models, but the 270M model's image input capability is implied by the family description), and generates text outputs. The model supports over 140 languages and was trained on 6 trillion tokens of diverse data including web documents, code, mathematics, and images, with a knowledge cutoff of August 2024.

Key Capabilities

  • Multimodal Understanding: Processes both text and image inputs to generate relevant text outputs.
  • Text Generation: Capable of generating creative text formats, chatbot responses, and summaries.
  • Multilingual Support: Trained on data in over 140 languages, enhancing global applicability.
  • Resource-Efficient Deployment: Its small size makes it suitable for deployment on devices with limited resources like laptops, desktops, or private cloud infrastructure.

Good for

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

Finetunes
1 models