Gemma 4 31B IT Release Details and Specs
Google released Gemma 4 31B IT on April 2, 2026. This text model features a 262,144-token context window and is available via AI Studio and the Gemini API.
Release Announcement and Availability
The official announcement date for this release is April 2, 2026. On this date, Google introduced gemma-4-31b-it alongside gemma-4-26b-a4b-it. Both models were released as part of the initial Gemma 4 launch. According to the source facts, these models are available on AI Studio and through the Gemini API.
- Model Name: Gemma 4 31B IT
- Provider: Google
- Family: Gemini
- Input Modalities: Text
- Output Modalities: Text
Verified Technical Specifications
The verified specifications for Gemma 4 31B IT indicate a context window of 262,144 tokens. The maximum output length is set at 32,768 tokens. The source confirms that open weights are true for this model. No pricing information is currently listed in the provided data. The model operates strictly with text inputs and produces text outputs.
Practical Evaluation Procedure
Engineers can evaluate the model by running standardized test suites against their specific use cases. First, measure latency and throughput using the Gemini API endpoints. Second, compare the quality of generated responses against existing baselines using relevant metrics. Finally, validate that the 262,144-token context window handles long-document tasks without truncation errors. These steps allow for a practical assessment of performance without assuming unverified benefits.
Primary sources
Frequently asked questions
When was Gemma 4 31B IT officially released?
The model was released on April 2, 2026, as part of the Gemma 4 launch.
What is the maximum context window for this model?
The context window is 262,144 tokens, with a maximum output of 32,768 tokens.