2.3× less energy than Qwen 3 235B.
Qwen 3 235B Environmental Impact
Open-source MoE flagship — strong multilingual performance
The figures below are for one quick question. A longer chat with follow-ups uses about 0.56 Wh, and an hour or two of agent work about 16.0 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
53% of a Google search.
71% of a Google search.
About 12× a drop of water and 12% of a teaspoon of water.
- Where it runsAlibaba Cloud (China / Global)
- Grid carbon intensity525 g CO₂/kWh · 33% renewable
- Compared with a Google searchabout the same as a search (0.3 Wh)
- Water~1,695 queries to fill 1 litre
Where Qwen 3 235B sits
#45 of 199 by energy per query. Lighter than 78% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
2.7× less energy than Qwen 3 235B.
8.0× less energy than Qwen 3 235B.
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
- 17.3 Wh
- Carbon
- 9.2 g
- Water
- 64 mL
A month of 5 chats a day, 5 days a week. The energy is about 1.4× a phone charge and 16% of a kettle boil.
Work out your own →- Energy
- 69.3 Wh
- Carbon
- 36.8 g
- Water
- 255 mL
A month of 20 chats a day, 5 days a week. The energy is about 5.8× a phone charge and 63% of a kettle boil.
Work out your own →- Energy
- 346.4 Wh
- Carbon
- 184.0 g
- Water
- 1.28 L
A month of 100 chats a day, 5 days a week. The energy is about 3.1× a kettle boil and 5% of a UK home's day.
Work out your own →How does Qwen 3 235B compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate Qwen3 235B at ~0.16 Wh for a quick single question, taken from the CLEER dataset (Sustainable AI Group, Sept 2026). The figure covers the full facility — accelerators, host servers, idle capacity and cooling. CLEER benchmarked the open weights directly (H200 x4 · batch 384). On the same basis a typical multi-turn chat comes to ~0.52 Wh and a typical agentic coding session to ~50 Wh, so how the model is used matters far more than which prompt you send. This replaces our earlier ~1.4 Wh estimate, which was extrapolated from 2025 benchmark figures on older hardware.
Power source & carbon
Alibaba Cloud serves Qwen primarily from data centres in China, with a grid carbon intensity of approximately 525 gCO₂/kWh. As an open-source model, it can also be self-hosted globally.
Water use
At ~0.59 mL per quick question, derived from the energy estimate at the ~3.7 L/kWh water factor we apply to this provider's infrastructure. Water scales directly with energy, so longer chats and agentic sessions use proportionally more.
About Qwen 3 235B
Qwen 3 235B is an open-source text and chat model from Alibaba, released in April 28, 2025, that runs well below the category average for energy consumption at 0.16 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 235B parameters, it open-source moe flagship — strong multilingual performance.
These figures are estimates derived from hardware specifications and API benchmarks — Alibaba has not published official energy data for Qwen 3 235B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
Qwen 3 235B in context
Key insights
- Open-source weights — can be self-hosted on infrastructure you control
What does your Qwen 3 235B usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use Qwen 3 235B.
Frequently asked questions
How much energy does Qwen 3 235B use per query?
Each Qwen 3 235B query consumes approximately 0.16 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).
What is Qwen 3 235B's carbon footprint?
Based on the carbon intensity of Alibaba Cloud (China / Global), each query produces approximately 0.09 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 Qwen 3 235B use?
Each query consumes approximately 0.59 mL of water, primarily used for cooling the data centers that process the request.
How does Qwen 3 235B compare to a Google search?
A Qwen 3 235B query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Qwen 3 235B uses 0.16 Wh.
Technical details
- Architecture
- Transformer Mixture-of-Experts (decoder-only)
- Parameters
- 235B
- Context window
- 128,000 tokens
- Release date
- 2025-04-28
- Open source
- Yes
- Training data cutoff
- 2025-03