3.3× less energy than Kimi K3.
Kimi K3 Environmental Impact
Largest open-weight model to date — 2.8T-parameter MoE with native vision
The figures below are for one quick question. A longer chat with follow-ups uses about 2.3 Wh, and an hour or two of agent work about 65.0 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
About 2.2× a Google search and 78% of a minute of laptop use.
About 2.8× a Google search and 16% of 10 m by car.
About 48× a drop of water and 48% of a teaspoon of water.
- Where it runsMoonshot AI Cloud (China) / self-hosted
- Grid carbon intensity525 g CO₂/kWh · 33% renewable
- Compared with a Google search2x more than a search (0.3 Wh)
- Water~417 queries to fill 1 litre
Where Kimi K3 sits
#133 of 199 by energy per query. Heavier than 66% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
1.6× less energy than Kimi K3.
1.6× less energy than Kimi K3.
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
- 70.4 Wh
- Carbon
- 36.8 g
- Water
- 260 mL
A month of 5 chats a day, 5 days a week. The energy is about 5.9× a phone charge and 64% of a kettle boil.
Work out your own →- Energy
- 281.4 Wh
- Carbon
- 147.2 g
- Water
- 1.04 L
A month of 20 chats a day, 5 days a week. The energy is about 2.6× a kettle boil and 4% of a UK home's day.
Work out your own →- Energy
- 1.41 kWh
- Carbon
- 736.1 g
- Water
- 5.20 L
A month of 100 chats a day, 5 days a week. The energy is about 13× a kettle boil and 19% of a UK home's day.
Work out your own →How does Kimi K3 compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
Kimi K3 is one of the few frontier-scale models whose energy has actually been benchmarked rather than inferred: because the weights are open, CLEER (Sustainable AI Group, Sept 2026) ran it directly on eight B300 accelerators and measured ~0.65 Wh for a quick single question, ~2.3 Wh for a typical multi-turn chat and ~88 Wh for a typical agentic session — full-facility figures including host servers, idle capacity and cooling. That makes it the heaviest open model in the dataset, and it is the main proxy CLEER uses to estimate Claude Fable 5. Weights followed the 16 July launch on 27 July under a custom licence.
Power source & carbon
Hosted inference runs on the Chinese grid at ~525 gCO2/kWh (Ember 2026). Open weights mean it is also widely self-hosted, where the footprint depends entirely on the local grid.
Water use
At ~2.4 mL per quick question on Chinese infrastructure (3.7 L/kWh combined water factor).
About Kimi K3
Kimi K3 is a 2800B-parameter text and chat model from Moonshot AI, released July 16, 2026. Largest open-weight model to date — 2.8T-parameter MoE with native vision. At 0.65 Wh per query, it uses 2x the energy of a Google search. It runs on a Mixture-of-Experts (2.8T total) with native vision architecture.
These figures are estimates derived from hardware specifications and API benchmarks — Moonshot AI has not published official energy data for Kimi K3. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
Kimi K3 in context
Key insights
- Open-source weights — can be self-hosted on infrastructure you control
The Moonshot AI Kimi family
One chart per tier, on a shared time axis. Hover a dot for details; click to open that version.
What does your Kimi K3 usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use Kimi K3.
Frequently asked questions
How much energy does Kimi K3 use per query?
Each Kimi K3 query consumes approximately 0.65 Wh of energy. This is 2x more than a traditional Google search (~0.3 Wh).
What is Kimi K3's carbon footprint?
Based on the carbon intensity of Moonshot AI Cloud (China) / self-hosted, each query produces approximately 0.34 g of CO2. The grid in this region has a carbon intensity of 525 g CO2/kWh with 33% renewable energy.
How much water does Kimi K3 use?
Each query consumes approximately 2 mL of water, primarily used for cooling the data centers that process the request.
How does Kimi K3 compare to a Google search?
A Kimi K3 query uses 2x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Kimi K3 uses 0.65 Wh.
Technical details
- Architecture
- Mixture-of-Experts (2.8T total) with native vision
- Parameters
- 2800B
- Context window
- 1,000,000 tokens
- Release date
- 2026-07-16
- Open source
- Yes