Multimodal

Phi-4 Multimodal Environmental Impact

Ultra-efficientEstimated

First multimodal Phi — speech + vision + text, #1 on OpenASR

Architecture
Multimodal Transformer (speech + vision + text)
Parameters
5.6B
Context
128,000 tokens
Provider
Microsoft
0.12 Wh
Energy per query
0.05 g
CO₂ per query
0.45 mL
Water per query
about the same as
vs Google search

Energy per query

0.12 Wh

about the same as a Google search (0.3 Wh)

CO2 per query

0.05 g

Global Average grid (475 gCO₂/kWh)

Water per query

0.45 mL

~2,222 queries to fill 1 litre

Processing location

Self-hosted / Azure

Provider

Microsoft

Category

Multimodal

Grid carbon intensity

475 g CO2/kWh (27% renewable)

How does Phi-4 Multimodal compare?

Ranked #7 of 152 models by energy per query

0 Wh0.4 Wh0.8 Wh1.2 Wh1.6 WhPhi-4MultimodalLLaMA 3.2 11BVisionLLaMA 3.2 90BVisionQwen 3.5 OmniGoogle search (0.3 Wh)

Detailed Breakdown

Energy Consumption

Phi-4 Multimodal is the first Phi model supporting speech, vision, and text in one 5.6B model. At ~0.12 Wh per query, it tops the OpenASR leaderboard for speech recognition and handles 20+ languages. Extremely efficient for on-device multimodal inference.

Power Source & Carbon

Open-source (MIT). Runs on mobile devices and edge hardware.

Water Usage

At ~0.45 mL per query. Zero on consumer devices.

About Phi-4 Multimodal

Phi-4 Multimodal is an open-source multimodal model from Microsoft, released in April 15, 2025, that runs well below the category average for energy consumption at 0.12 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 5.6B parameters, it first multimodal phi — speech + vision + text, #1 on openasr.

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

Phi-4 Multimodal in Context

1.1 kWh
per year

Your yearly Phi-4 Multimodal footprint

At 25 queries per day, your annual Phi-4 Multimodal usage consumes 1.1 kWh — comparable to running a LED light bulb for a month. That produces 0.5 kg of CO₂.

Key Insights

Top 10 most energy-efficient model across 152 models tracked
Uses less than a third of the average energy for multimodal models
Open-source weights — can be self-hosted on infrastructure you control

What does your Phi-4 Multimodal usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Phi-4 Multimodal.

Calculate My Compute

Frequently Asked Questions

How much energy does Phi-4 Multimodal use per query?

Each Phi-4 Multimodal query consumes approximately 0.12 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is Phi-4 Multimodal's carbon footprint?

Based on the carbon intensity of Self-hosted / Azure, each query produces approximately 0.05 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 Phi-4 Multimodal use?

Each query consumes approximately 0.45 mL of water, primarily used for cooling the data centers that process the request.

How does Phi-4 Multimodal compare to a Google search?

A Phi-4 Multimodal query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Phi-4 Multimodal uses 0.12 Wh.

Technical Details

Architecture

Multimodal Transformer (speech + vision + text)

Parameters

5.6B

Context window

128,000 tokens

Release date

2025-04-15

Open source

Yes

Training data cutoff

2025-03