2.9× less energy than Mistral 7B.
Mistral 7B Environmental Impact
Foundational open-source model that launched Mistral AI
The figures below are for one quick question. A longer chat with follow-ups uses about 0.20 Wh, and an hour or two of agent work about 5.8 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
19% of a Google search.
2% of a Google search.
About 1.2× a drop of water and 1% of a teaspoon of water.
- Where it runsSelf-hosted (varies)
- Grid carbon intensity458 g CO₂/kWh · 32% renewable
- Compared with a Google searchabout the same as a search (0.3 Wh)
- Water~17,241 queries to fill 1 litre
Where Mistral 7B sits
#20 of 199 by energy per query. Lighter than 90% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
1.8× less energy than Mistral 7B.
2.1× less energy than Mistral 7B.
What a month of use adds up to
Pick how much you use it. Based on one quick use at a time, five days a week.
- Energy
- 6.3 Wh
- Carbon
- 0.31 g
- Water
- 6 mL
A month of 5 chats a day, 5 days a week. The energy is 52% of a phone charge.
Work out your own →- Energy
- 25.1 Wh
- Carbon
- 1.3 g
- Water
- 25 mL
A month of 20 chats a day, 5 days a week. The energy is about 2.1× a phone charge and 23% of a kettle boil.
Work out your own →- Energy
- 125.6 Wh
- Carbon
- 6.3 g
- Water
- 126 mL
A month of 100 chats a day, 5 days a week. The energy is about 1.1× a kettle boil and 2% of a UK home's day.
Work out your own →How does Mistral 7B compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate Mistral 7B at ~0.058 Wh for a quick single question. The open-weight models CLEER has benchmarked directly follow a clear pattern: roughly 0.02 Wh plus 0.005 Wh per billion parameters active on each token (our fit across 11 models from 3B to 49B active). Mistral 7B activates ~7.3B (it is a dense model, so every parameter is active), which gives ~0.058 Wh when served from a batched data-centre deployment. Run locally, the figure depends entirely on your hardware. This is our extrapolation, not a CLEER figure or a measurement. It replaces our earlier ~0.25 Wh estimate, which was built on 2025 benchmark figures for older hardware.
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 use
At ~0.058 mL per quick question, derived from the energy estimate at the ~1 L/kWh water factor we apply to this model's infrastructure. Water scales directly with energy, so longer chats, reasoning and agentic sessions use proportionally more.
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 0.06 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
The Mistral AI Mistral family
One chart per tier, on a shared time axis. Hover a dot for details; click to open that version.
6 versions across 2 tiers. Lightest: Mistral 7B (0.06 Wh); heaviest: Mistral Large 2 (1.8 Wh). Charts share a time axis but each tier has its own energy scale, so its trend is clear; the percentage is the change from a tier’s first version to its latest.
What does your Mistral 7B usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use Mistral 7B.
Frequently asked questions
How much energy does Mistral 7B use per query?
Each Mistral 7B query consumes approximately 0.06 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 0.00 g of CO2. The grid in this region has a carbon intensity of 458 g CO2/kWh with 32% renewable energy.
How much water does Mistral 7B use?
Each query consumes approximately 0.06 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 0.06 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