Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is a multimodal model from Google handling text and image input (with audio supported on small models) and generating text output.

Model ID	`gemma-4-26b-a4b-it-maas`
Modalities	Text Input and output Image Input only Audio Not supported Video Not supported
Capabilities	Function calling Supported Structured output Supported Thinking Not supported
Consumption options	Provisioned Throughput Supported Batch inference Not supported Pay-as-you-go Standard PayGo Supported Fixed quota Not supported
Supported regions	Model availability	Global: `global`
Supported regions	ML processing	Multi-region: `us`
Quotas	`global`: 128,000 maximum output, 262,144 context length
Versions	`gemma-4-26b-a4b-it-maas` Launch stage: Experimental Release date: April 3, 2026

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-07-23 UTC.

Gemma 4 26B A4B IT Stay organized with collections Save and categorize content based on your preferences.