Text / Chat

Gemma 3 4B Environmental Impact

Ultra-efficientEstimated

Small multimodal open model for edge and mobile

Architecture
Multimodal Transformer (text + image)
Parameters
4B
Context
128,000 tokens
Provider
Google
0.08 Wh
Energy per query
0.03 g
CO₂ per query
0.30 mL
Water per query
about the same as
vs Google search

Energy per query

0.08 Wh

about the same as a Google search (0.3 Wh)

CO2 per query

0.03 g

Global Average grid (475 gCO₂/kWh)

Water per query

0.30 mL

~3,333 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 4B compare?

Ranked #4 of 152 models by energy per query

0 Wh0.07 Wh0.14 Wh0.21 Wh0.28 WhGemma 3 4BLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 Nano

Detailed Breakdown

Energy Consumption

Gemma 3 4B is a multimodal open model that handles both text and images at just 4B parameters. At ~0.08 Wh per query, it can run on mobile devices and edge hardware, making it one of the most efficient multimodal models available.

Power Source & Carbon

Fully open-source. Can run on smartphones, laptops, and edge devices — energy depends entirely on deployment.

Water Usage

At ~0.3 mL per query. On-device inference uses zero water.

About Gemma 3 4B

At 0.08 Wh per query, Gemma 3 4B is one of the most energy-efficient AI models in existence — ranked #4 across our entire dataset of 152 models. With just 4B parameters, it proves that useful AI doesn't have to be expensive to run. As an open-source model, it can be deployed on any hardware, including personal devices. Google released it in March 12, 2025 as a text and chat model: small multimodal open model for edge and mobile.

These figures are estimates derived from hardware specifications and API benchmarks — Google has not published official energy data for Gemma 3 4B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Key Insights

Top 10 most energy-efficient model across 152 models tracked
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 4B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Gemma 3 4B.

Calculate My Compute

Frequently Asked Questions

How much energy does Gemma 3 4B use per query?

Each Gemma 3 4B query consumes approximately 0.08 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is Gemma 3 4B's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.03 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 4B use?

Each query consumes approximately 0.30 mL of water, primarily used for cooling the data centers that process the request.

How does Gemma 3 4B compare to a Google search?

A Gemma 3 4B query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Gemma 3 4B uses 0.08 Wh.

Technical Details

Architecture

Multimodal Transformer (text + image)

Parameters

4B

Context window

128,000 tokens

Release date

2025-03-12

Open source

Yes

Training data cutoff

2025-02