Using Gemma 4 12B on Kaggle Models

Implementation guide · Gemma 4 · Google DeepMind

Open Source

Kaggle Models exposes Gemma 4 12B through model ID google/gemma-4. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

1
Create an account at Kaggle Models and generate an API key.
2
Use the Kaggle Models SDK or REST API to call google/gemma-4 — see the documentation for request format.

API Portal Documentation Model Card

Code Examples

See Kaggle Models documentation for integration details.

Pricing on Kaggle Models

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsAudio

About Gemma 4 12B

Google DeepMind's 12B open-weight multimodal model (Apache 2.0), designed to run on a 16GB laptop. First medium-sized model with native audio ingestion alongside text and image. Unified encoder-free decoder-only architecture. Supports 140+ languages. MMLU Pro: 77.2%.

Full model details →

Model Specs

Released2026-06-03

Parameters12B

Context256k

ArchitectureDecoder Only

Knowledge cutoff2025-01

Google