Text / Chat

Mistral Small 4 Environmental Impact

Ultra-efficientEstimated

Unified reasoning + multimodal + coding in one small model

Architecture
Dense Transformer (unified capabilities)
Context
128,000 tokens
Provider
Mistral AI
0.40 Wh
Energy per query
0.02 g
CO₂ per query
0.30 mL
Water per query
about the same as
vs Google search

Energy per query

0.40 Wh

about the same as a Google search (0.3 Wh)

CO2 per query

0.02 g

France grid (50 gCO₂/kWh)

Water per query

0.30 mL

~3,333 queries to fill 1 litre

Processing location

Mistral AI (France) / self-hosted

Provider

Mistral AI

Category

Text / Chat

Grid carbon intensity

50 g CO2/kWh (90% renewable)

How does Mistral Small 4 compare?

Ranked #27 of 152 models by energy per query

0 Wh0.1 Wh0.2 Wh0.3 Wh0.4 WhLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 NanoMistral Small 4Google search (0.3 Wh)

Detailed Breakdown

Energy Consumption

Mistral Small 4 unifies Magistral (reasoning), Pixtral (multimodal), and Devstral (coding) capabilities into a single versatile small model. At ~0.4 Wh per query, it replaces three specialised models with one efficient general-purpose model. Open-source.

Power Source & Carbon

Via Mistral API, runs on France's clean nuclear grid (50 g CO2/kWh). Also self-hostable.

Water Usage

At ~0.3 mL per query. Zero when self-hosted on consumer hardware.

About Mistral Small 4

Mistral Small 4 is an open-source text and chat model from Mistral AI, released in March 16, 2026, that runs well below the category average for energy consumption at 0.40 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. It unified reasoning + multimodal + coding in one small model.

Mistral Small 4 benefits from running in France, one of the cleaner grid regions in our dataset at 50 gCO₂/kWh with 90% renewable energy. The same model running in a coal-heavy region would produce significantly more carbon per query.

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

Mistral Small 4 in Context

3.6 kWh
per year

Your yearly Mistral Small 4 footprint

At 25 queries per day, your annual Mistral Small 4 usage consumes 3.6 kWh — comparable to running a LED light bulb for a month. That produces 0.2 kg of CO₂.

Key Insights

Uses less than a third of the average energy for text and chat models
Runs on a 90% renewable grid — among the cleanest AI inference locations
Open-source weights — can be self-hosted on infrastructure you control

What does your Mistral Small 4 usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Mistral Small 4.

Calculate My Compute

Frequently Asked Questions

How much energy does Mistral Small 4 use per query?

Each Mistral Small 4 query consumes approximately 0.40 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is Mistral Small 4's carbon footprint?

Based on the carbon intensity of Mistral AI (France) / self-hosted, each query produces approximately 0.02 g of CO2. The grid in this region has a carbon intensity of 50 g CO2/kWh with 90% renewable energy.

How much water does Mistral Small 4 use?

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

How does Mistral Small 4 compare to a Google search?

A Mistral Small 4 query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Mistral Small 4 uses 0.40 Wh.

Technical Details

Architecture

Dense Transformer (unified capabilities)

Context window

128,000 tokens

Release date

2026-03-16

Open source

Yes

Training data cutoff

2026-02