How much energy does Qwen3-235B-A22B use?

Alibaba · released 2025-04-29

Qwen3-235B-A22B uses about 0.115 Wh of electricity to answer a typical question. A long, complex answer costs about 23× more, at 2.69 Wh. That places it 174 of 277 among the models we can measure, and every figure here is calculated the same way as every other model.

A typical question

0.115 Wh

under 0.1 g CO₂·under a metre of driving

A long, complex answer

2.69 Wh

1.2 g CO₂·≈ 5 metres (16 feet) of driving

Capability

139.3

Energy rank

174 of 277

Human votes

1393

How capable is it, really?

The capability figure of 139.35 is a composite over 58 benchmarks, Epoch AI's Capabilities Index, which folds in software engineering, agentic tool use, long-context comprehension and creative writing as well as science reasoning. It is one number standing for a lot of separate tests, so treat a small gap between two models as noise rather than a ranking.

37,484 people have voted on it in blind head-to-head comparisons on LMArena, giving it a rating of 1393. This is the only figure here that measures whether anyone actually prefers the answers, rather than how the model scores on a test. Broken down, people rate it 1398 on coding, 1356 on creative writing, 1362 on following instructions.

What this figure is

Calculated Calculated from a published parameter count. Every model on this site is calculated the same way, so the comparison holds even where the absolute value carries uncertainty. Our figures are good to roughly a factor of two to three, which is why we only ever state a difference of 5× or more.

Is there a better choice?

A lighter model that does the job

Claude Haiku 5.5

Anthropic · capability 159.0. It scores higher than Qwen3-235B-A22B on Epoch's Capabilities Index (158.98 against 139.35), the composite over 58 benchmarks that the capability figure above comes from, and uses about 5.2× less energy per answer: 0.515 Wh against 2.69 Wh. It has not faced human head-to-head voting, where Qwen3-235B-A22B carries 37,484 votes, worth weighing.

What Alibaba publishes

Energy cannot be worked out without knowing how big a model is. Of the 45 models from Alibaba that we track, 24 can be assessed at all, the rest publish too little for anyone outside the company to calculate anything.

Where these figures come from

Capability and the roster come from Epoch AI, whose Capabilities Index is the 58-benchmark composite quoted above. Energy is calculated with EcoLogits and calibrated against laboratory measurements from ML.ENERGY. Human preference comes from LMArena. All four are public and free; the full method is here.

These figures are published under CC BY 4.0, use them anywhere, including commercially, with credit to The AI Footprint.

Compare it with something

Compare Qwen3-235B-A22B with another model

Or work out what a year of using it adds up to, for you or for a whole organisation.

Figure calculated 2026-10-17 · how these numbers are made · the full comparison of 277 models