T5gemma S S Prefixlm
T5Gemma is a family of lightweight yet powerful encoder-decoder models developed by Google, adapted from pretrained decoder-only models to offer a favorable quality-efficiency trade-off. These models excel at generative tasks such as question answering, summarization, and reasoning, and their encoders also provide strong performance on discriminative tasks like classification and understanding benchmarks.
Input
Output
Context
16K
Max Output
1K
Parameters
300M
Technical Specifications
Model TypeChat
Context Window16,000 tokens
Max Output Tokens512 tokens
Parameters300M
Release DateJun 19, 2025
Training CutoffNot available
Licensegemma
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Estimated GPU Requirements for T5gemma S S Prefixlm
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 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.