unsloth/gemma-4-31B-it

VISIONConcurrency Cost:2Model Size:31BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Mar 31, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The unsloth/gemma-4-31B-it is a 30.7 billion parameter instruction-tuned multimodal language model developed by Google DeepMind, part of the Gemma 4 family. It features a 256K token context window and supports text and image input, excelling in reasoning, coding, and agentic workflows. This model is designed for deployment on consumer GPUs and workstations, offering enhanced capabilities in multimodal understanding and native function-calling.

Loading preview...

Overview

The unsloth/gemma-4-31B-it model is a 30.7 billion parameter instruction-tuned variant from the Gemma 4 family, developed by Google DeepMind. It is a multimodal model capable of processing text and image inputs, generating text outputs, and supporting a substantial 256K token context window. This model is optimized for advanced reasoning, coding tasks, and agentic workflows, making it suitable for complex applications.

Key Capabilities

  • Multimodal Understanding: Processes text and images, with support for variable aspect ratios and resolutions. It can analyze video by processing sequences of frames.
  • Advanced Reasoning: Designed with configurable thinking modes to facilitate step-by-step reasoning.
  • Extended Context Window: Features a 256K token context window, enabling deep awareness for long-context tasks.
  • Enhanced Coding & Agentic Capabilities: Achieves significant improvements in coding benchmarks and includes native function-calling support for autonomous agents.
  • Multilingual Support: Pre-trained on over 140 languages with out-of-the-box support for 35+ languages.
  • Native System Prompt Support: Introduces native support for the system role, allowing for more structured and controllable conversations.

Good For

  • Content Creation: Generating creative text formats, marketing copy, and email drafts.
  • Conversational AI: Powering chatbots, virtual assistants, and interactive applications.
  • Research & Education: Serving as a foundation for VLM and NLP research, language learning tools, and knowledge exploration.
  • Image Data Extraction: Interpreting and summarizing visual data, including OCR, document parsing, and chart comprehension.
  • Complex Reasoning Tasks: Applications requiring detailed logical reasoning and problem-solving.

Finetunes
12 models