LLM Reference

Gemma 4 12B IT on Kaggle Models

Gemma 4 · Google DeepMind

Open Source

Last refreshed 2026-06-03. Next refresh: weekly.

Why use Gemma 4 12B IT on Kaggle Models?

Kaggle Models offers Gemma 4 12B IT with competitive pricing. 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.

Compare Gemma 4 12B IT across 2 providers to find the best fit for your use case
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: google/gemma-4
Model ID
google/gemma-4

Request example

Curated snippets for this provider are not sourced yet. Use Kaggle Models documentation with model ID google/gemma-4.

Gotchas

  • Use provider model ID "google/gemma-4", not the LLMReference slug "gemma-4-12b-it".

Compare Gemma 4 12B IT Across Providers

ProviderInput (per 1M)Output (per 1M)
Hugging Face Inference Endpoints
Kaggle Models

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsAudio

About Gemma 4 12B IT

Instruction-tuned 12B Gemma 4 model with native text, image, video, and audio input through an encoder-free unified architecture. It runs on 16 GB VRAM in BF16, supports a 256K context window, configurable thinking mode, function calling, structured outputs, and 140+ languages, making it the mid-sized Gemma 4 option between E4B and the 26B MoE.

FAQ

What is the context window for Gemma 4 12B IT on Kaggle Models?

Gemma 4 12B IT supports a 262k token context window on Kaggle Models.

What API model ID do I use for Gemma 4 12B IT on Kaggle Models?

Use the model ID google/gemma-4 when calling Kaggle Models's API.

Who created Gemma 4 12B IT?

Gemma 4 12B IT was created by Google DeepMind as part of the Gemma 4 model family.

Is Gemma 4 12B IT open source?

Gemma 4 12B IT is open source according to the seed data.

Get Started

Model Specs

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

Related Models on Kaggle Models