Text / Chat

Mistral 7B Environmental Impact

Ultra-efficientEstimated

Foundational open-source model that launched Mistral AI

Architecture
Dense Transformer with Sliding Window Attention
Parameters
7.3B
Context
32,000 tokens
Provider
Mistral AI
0.25 Wh
Energy per query
0.16 g
CO₂ per query
1 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

0.16 g

Global Average grid (475 gCO₂/kWh)

Water per query

1 mL

~909 queries to fill 1 litre

Processing location

Self-hosted (varies)

Provider

Mistral AI

Category

Text / Chat

Grid carbon intensity

475 g CO2/kWh (27% renewable)

How does Mistral 7B compare?

Ranked #14 of 152 models by energy per query

0 Wh0.07 Wh0.14 Wh0.21 Wh0.28 WhLLaMA 3.2 1BGemini 1.5 ProMistral 7BGPT-4.1 Nano

Detailed Breakdown

Energy Consumption

Mistral 7B was a breakthrough in small model efficiency when released, outperforming LLaMA 2 13B on most benchmarks. At ~0.25 Wh per query, it remains one of the most efficient capable models and has been fine-tuned into thousands of variants.

Power Source & Carbon

Fully open-source (Apache 2.0), deployable anywhere. One of the most self-hosted models globally. Mistral AI is based in Paris, France, where the grid is 90% low-carbon (nuclear + renewables).

Water Usage

At ~1.1 mL per query, Mistral 7B has a minimal water footprint. When self-hosted on consumer hardware, water usage drops to zero.

About Mistral 7B

Mistral 7B is an open-source text and chat model from Mistral AI, released in September 27, 2023, 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 7.3B parameters, it foundational open-source model that launched mistral ai.

These figures are estimates derived from hardware specifications and API benchmarks — Mistral AI has not published official energy data for Mistral 7B. 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

What does your Mistral 7B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Mistral 7B.

Calculate My Compute

Frequently Asked Questions

How much energy does Mistral 7B use per query?

Each Mistral 7B query consumes approximately 0.25 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is Mistral 7B's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.16 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 Mistral 7B use?

Each query consumes approximately 1 mL of water, primarily used for cooling the data centers that process the request.

How does Mistral 7B compare to a Google search?

A Mistral 7B query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Mistral 7B uses 0.25 Wh.

Technical Details

Architecture

Dense Transformer with Sliding Window Attention

Parameters

7.3B

Context window

32,000 tokens

Release date

2023-09-27

Open source

Yes

Training data cutoff

2023-09