# t5gemma 9b 9b prefixlm it [Canonical model page](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `google-t5gemma-9b-9b-prefixlm-it`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about t5gemma 9b 9b prefixlm it AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-identity) · [Access](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-access) · [Inputs & outputs](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-modalities) · [License](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-license) · [Model details](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-research) · [Weight details](https://headlessthrones.com/models/google-t5gemma-9b-9b-prefixlm-it#model-answer-repository) ### Which t5gemma 9b 9b prefixlm it does this page describe? t5gemma 9b 9b prefixlm it is a model record from **Google** in the t5gemma family. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it) The recorded model identifier or checkpoint is `google/t5gemma-9b-9b-prefixlm-it`. Use that exact identifier when checking documentation or a provider listing. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it) ### How can you access t5gemma 9b 9b prefixlm it? The catalog documents **Open weights** access for t5gemma 9b 9b prefixlm it. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it) As of the catalog check, this version was listed as available. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it) Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. ### What can t5gemma 9b 9b prefixlm it receive and generate? Documented inputs: **Text**. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) Documented outputs: **Text**. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What license is recorded for t5gemma 9b 9b prefixlm it? The recorded license label is **gemma**. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it) Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service. ### What distinguishes t5gemma 9b 9b prefixlm it? These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results. **Exact encoder-decoder checkpoint**: 9B encoder and 9B decoder, adapted with PrefixLM; instruction-tuned checkpoint. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) **Architecture and intended tasks**: Encoder-decoder research model for English text generation, including question answering, summarization and reasoning. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) **Training adaptation**: The documented adaptation stage uses two trillion tokens. The card separates the original decoder pretraining from encoder-decoder adaptation. [Source](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) ### What is documented about the t5gemma 9b 9b prefixlm it checkpoint? This evidence refers to `google/t5gemma-9b-9b-prefixlm-it` at recorded revision `b72b180286acafe42287e8287684dd49e0a7b846`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Safetensors metadata records **20,333,401,088 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Recorded architecture class: `T5GemmaForConditionalGeneration`. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Repository task tag: `text-generation`. A task tag identifies a distribution category; it does not measure performance on that task. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Listed library: `transformers`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Repository access gate: `manual`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) **Catalog qualifications:** Official Google-published checkpoint. Base/pretrained and instruction-tuned variants remain distinct; platform and quantized packaging copies are excluded. Hosted API availability not inferred. [Source 1](https://huggingface.co/api/models/google/t5gemma-9b-9b-prefixlm-it) · [Source 2](https://huggingface.co/google/t5gemma-9b-9b-prefixlm-it/resolve/b72b180286acafe42287e8287684dd49e0a7b846/README.md) **Evidence still missing here:** context or input capacity, knowledge and training-data cutoffs, and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other t5gemma models from Google. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [t5gemma 2 1b 1b](https://headlessthrones.com/models/google-t5gemma-2-1b-1b) Open weights ### [t5gemma 2 270m 270m](https://headlessthrones.com/models/google-t5gemma-2-270m-270m) Open weights ### [t5gemma 2 4b 4b](https://headlessthrones.com/models/google-t5gemma-2-4b-4b) Open weights ### [t5gemma 2b 2b prefixlm](https://headlessthrones.com/models/google-t5gemma-2b-2b-prefixlm) Open weights ### [t5gemma 2b 2b prefixlm it](https://headlessthrones.com/models/google-t5gemma-2b-2b-prefixlm-it) Open weights ### [t5gemma 2b 2b ul2](https://headlessthrones.com/models/google-t5gemma-2b-2b-ul2) Open weights