Get API access
Model release

Gemma 4 26B A4B IT Release Details

Google released Gemma 4 26B A4B IT on April 2, 2026. It is available via AI Studio and the Gemini API with a 262,144-token context window.

Released Published 3 min readModel evidence ↗
Gemma 4 26B A4B IT release illustration — Google

Release Announcement and Availability

The source event date for this release is April 2, 2026. This historical date distinguishes the announcement from the current publication date of this article. On that day, Google released gemma-4-26b-a4b-it and gemma-4-31b-it as part of the Gemma 4 launch. Official changelogs confirm that both models are available on AI Studio and through the Gemini API. The provider is identified as Google, and the model belongs to the Gemini family.

Documented Technical Specifications

The Gemma 4 26B A4B IT model processes text inputs and generates text outputs. The verified facts specify a context window of 262,144 tokens and a maximum output limit of 32,768 tokens. The source confirms that open weights are true for this specific model iteration. No pricing information is provided in the verified facts. The model is listed in the official Gemini models API documentation, confirming its status as an active offering within the ecosystem.

  • Input Modalities: Text
  • Output Modalities: Text
  • Context Window: 262,144 tokens
  • Max Output Tokens: 32,768
  • Open Weights: Confirmed

Proposed Evaluation Procedure

Engineers can evaluate the model by defining specific test cases relevant to their application needs. First, prepare a dataset of prompts that represent typical user queries or technical tasks. Second, send these prompts to the model via the Gemini API or AI Studio interface. Third, measure the response quality against predefined criteria such as accuracy, coherence, or format compliance. Fourth, compare the results with baseline expectations or previous internal benchmarks if available. Finally, validate whether the 262,144-token context window handles long-document inputs without truncation errors. This process allows for a practical assessment of the model's capabilities without assuming unverified performance metrics.

Primary sources

QUICK ANSWERS

Frequently asked questions

When was Gemma 4 26B A4B IT released?

The model was released on April 2, 2026, as part of the Gemma 4 launch.

What are the context limits for this model?

The model supports a context window of 262,144 tokens and has a maximum output length of 32,768 tokens.