Diffusiongemma 26B A4B It
DiffusionGemma is a generative chat model developed by Google DeepMind, capable of handling multimodal inputs including text and images to generate text output. It is particularly suited for high-speed generation, leveraging its Mixture-of-Experts (MoE) architecture and discrete diffusion mechanism to improve tokens per second while maintaining deployability.
Input
Output
Context
262K
Max Output
33K
Parameters
25.8B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters25.8B
Release DateJun 9, 2026
Training CutoffJan 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Diffusiongemma 26B A4B It
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.