unsloth/gemma-4-E4B

VISIONConcurrent Unit Cost:1Model Size:7.9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 31, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The unsloth/gemma-4-E4B is a 4.5 billion effective parameter multimodal language model developed by Google DeepMind, part of the Gemma 4 family. This model handles text, image, and audio inputs with a 128K token context window, and is optimized for reasoning, coding, and agentic workflows. It features a hybrid attention mechanism for efficient processing and is designed for deployment on devices ranging from high-end phones to laptops.

Loading preview...

Overview

unsloth/gemma-4-E4B is a 4.5 billion effective parameter model from the Gemma 4 family, developed by Google DeepMind. It is a multimodal model capable of processing text, image, and audio inputs, and generating text outputs. The model features a 128K token context window and supports over 140 languages. It utilizes a hybrid attention mechanism, combining local sliding window attention with global attention, to balance processing speed and deep contextual awareness, and employs Per-Layer Embeddings (PLE) for parameter efficiency.

Key Capabilities

  • Multimodality: Processes text, images (with variable aspect ratio and resolution), and audio natively.
  • Reasoning: Designed with configurable thinking modes for step-by-step reasoning.
  • Extended Context: Supports a 128K token context window.
  • Coding & Agentic: Enhanced performance in coding benchmarks and native function-calling support for autonomous agents.
  • System Prompt Support: Introduces native support for the system role for structured conversations.
  • Optimized for On-Device: Smaller models like E4B are specifically designed for efficient local execution.

Good For

  • Multimodal Applications: Ideal for tasks requiring understanding and generation across text, image, and audio.
  • Reasoning Tasks: Benefits from its built-in reasoning mode for complex problem-solving.
  • Coding & Agentic Workflows: Strong performance in code generation, completion, and agentic applications with function calling.
  • On-Device Deployment: Suitable for efficient execution on mobile devices and laptops due to its optimized architecture.

Finetunes
19 models