LLM Reference

T5Gemma Models by Google DeepMind

Google DeepMindGemmaOpen weights
1 model2025

Details

ResearcherGoogle DeepMind
LicenseGemma
Commercial useCommercial use: conditional
Models1
Released2025

Capabilities

Function CallingAll models
Tool UseAll models
Structured OutputsAll models

Links

Website

About

T5Gemma is Google's open encoder-decoder model family based on Gemma 2, with a separate T5Gemma 2 line based on Gemma 3. Google treats T5Gemma as distinct from Gemma 3 decoder-only models.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view
T5GemmaCurrent

Use when the workload needs 2B parameters, tool use, and function calling.

2025-072B parameterstool usefunction calling

Release Timeline

1 release group
2025-07
1 current
T5Gemma
2B parameterstool usefunction calling
Current

Specifications(1 models)

T5Gemma model specifications comparison
ModelReleasedParametersFn CallingTool UseStructured Outputs
T5Gemma2025-072BYesYesYes

Available From(1 provider)

Frequently Asked Questions

What is T5Gemma used for?
T5Gemma is used for agent workflows and tool use, structured outputs, and coding. The family description and listed model capabilities point to those workloads as the best fit.
How does T5Gemma compare to Gemma 4?
T5Gemma by Google DeepMind is strongest where you need agent workflows and tool use, while Gemma 4 by Google DeepMind is the closest related family to check for multimodal. T5Gemma has 1 listed variant, while Gemma 4 reaches up to 256k context, so compare the specs and pricing tables before choosing a production model.
Which T5Gemma model should I use?
If price is the main constraint, use the pricing table first because T5Gemma does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate T5Gemma with tool use, function calling, and structured outputs.