LLM Reference

Using Gemma 4 12B on Kaggle Models

Implementation guide · Gemma 4 · Google DeepMind

Open Source

Quick Start

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

Code Examples

See Kaggle Models documentation for integration details.

About Kaggle Models

Kaggle Models hosts model collections with downloadable artifacts, examples, and notebook integration. For Gemma 4 12B, the confirmed source-backed availability is the official google/gemma-4 collection rather than a managed per-token API endpoint.

Kaggle Models is Google Kaggle's model hub for discovering and downloading public machine learning models, including official Google Gemma weights for local and notebook-based use.

Pricing on Kaggle Models

Capabilities

VisionMultimodalReasoningFunction CallingTool UseAudio

About Gemma 4 12B

Base pre-trained 12B Gemma 4 model with an encoder-free unified multimodal architecture for text, image, video, and audio input. It supports a 256K context window and is intended for fine-tuning, research, and self-hosted local deployment in the gap between Gemma 4 E4B and the larger 26B MoE / 31B dense variants.

Model Specs

Released2026-06-03
Parameters11.9B
Context256k
Architectureencoder_free_unified_multimodal
Knowledge cutoff2025-01

Provider

Kaggle Models

Google