Text / Chat

Gemma 3 12B Environmental Impact

Ultra-efficientEstimated

Mid-size multimodal open model — strong single-GPU performance

Architecture
Multimodal Transformer (text + image)
Parameters
12B
Context
128,000 tokens
Provider
Google
0.25 Wh
Energy per query
0.10 g
CO₂ per query
0.90 mL
Water per query
about the same as
vs Google search

Energy per query

0.25 Wh

about the same as a Google search (0.3 Wh)

CO2 per query

0.10 g

Global Average grid (475 gCO₂/kWh)

Water per query

0.90 mL

~1,111 queries to fill 1 litre

Processing location

Self-hosted (varies)

Provider

Google

Category

Text / Chat

Grid carbon intensity

475 g CO2/kWh (27% renewable)

How does Gemma 3 12B compare?

Ranked #15 of 152 models by energy per query

0 Wh0.07 Wh0.14 Wh0.21 Wh0.28 WhLLaMA 3.2 1BGemini 1.5 ProGemma 3 12BGPT-4.1 Nano

Detailed Breakdown

Energy Consumption

Gemma 3 12B offers a strong capability/efficiency balance at ~0.25 Wh per query. It handles text and image inputs while fitting comfortably on a single consumer GPU. Popular for fine-tuning and local deployment.

Power Source & Carbon

Fully open-source. Popular on Hugging Face and Ollama for local deployment.

Water Usage

At ~0.9 mL per query. Zero water when self-hosted on consumer hardware.

About Gemma 3 12B

Gemma 3 12B is an open-source text and chat model from Google, released in March 12, 2025, that runs well below the category average for energy consumption at 0.25 Wh per query. Because its weights are publicly available, it can be self-hosted on any infrastructure — meaning its carbon footprint depends entirely on where and how you choose to run it. At 12B parameters, it mid-size multimodal open model — strong single-gpu performance.

These figures are estimates derived from hardware specifications and API benchmarks — Google has not published official energy data for Gemma 3 12B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Key Insights

Uses less than a third of the average energy for text and chat models
Open-source weights — can be self-hosted on infrastructure you control

Google Gemma Family

What does your Gemma 3 12B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Gemma 3 12B.

Calculate My Compute

Frequently Asked Questions

How much energy does Gemma 3 12B use per query?

Each Gemma 3 12B query consumes approximately 0.25 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is Gemma 3 12B's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.10 g of CO2. The grid in this region has a carbon intensity of 475 g CO2/kWh with 27% renewable energy.

How much water does Gemma 3 12B use?

Each query consumes approximately 0.90 mL of water, primarily used for cooling the data centers that process the request.

How does Gemma 3 12B compare to a Google search?

A Gemma 3 12B query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Gemma 3 12B uses 0.25 Wh.

Technical Details

Architecture

Multimodal Transformer (text + image)

Parameters

12B

Context window

128,000 tokens

Release date

2025-03-12

Open source

Yes

Training data cutoff

2025-02