Text / Chat

Qwen 3.5 72B Environmental Impact

StandardEstimated

Flagship open-source model with hybrid thinking — Apache 2.0

Architecture
Dense Transformer with hybrid thinking/non-thinking
Parameters
72B
Context
262,000 tokens
Provider
Alibaba
1.1 Wh
Energy per query
0.61 g
CO₂ per query
4 mL
Water per query
4x more than
vs Google search

Energy per query

1.1 Wh

4x more than a Google search (0.3 Wh)

CO2 per query

0.61 g

China grid (550 gCO₂/kWh)

Water per query

4 mL

~244 queries to fill 1 litre

Processing location

Alibaba Cloud (China) / self-hosted

Provider

Alibaba

Category

Text / Chat

Grid carbon intensity

550 g CO2/kWh (30% renewable)

How does Qwen 3.5 72B compare?

Ranked #60 of 152 models by energy per query

0 Wh0.3 Wh0.6 Wh0.9 Wh1.2 WhLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 NanoQwen 3.5 72BGoogle search (0.3 Wh)

Detailed Breakdown

Energy Consumption

Qwen 3.5 72B is one of the most capable open-source models available, with native vision, 262K context, and hybrid thinking/non-thinking modes. At ~1.1 Wh per non-thinking query, it is competitive with commercial models. The hybrid mode allows users to trade quality for efficiency. Apache 2.0 licensed.

Power Source & Carbon

Available via Alibaba Cloud or self-hosted. Alibaba Cloud operates data centres in China (550 g CO2/kWh) and internationally. Being open-source, it's widely deployed on lower-carbon infrastructure globally.

Water Usage

At ~4.1 mL per query on Chinese infrastructure. Self-hosted globally, water varies by location.

About Qwen 3.5 72B

Qwen 3.5 72B is an open-source text and chat model from Alibaba, released in February 15, 2026, that runs well below the category average for energy consumption at 1.1 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 72B parameters, it flagship open-source model with hybrid thinking — apache 2.0.

These figures are estimates derived from hardware specifications and API benchmarks — Alibaba has not published official energy data for Qwen 3.5 72B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Qwen 3.5 72B in Context

10.0 kWh
per year

Your yearly Qwen 3.5 72B footprint

At 25 queries per day, your annual Qwen 3.5 72B usage consumes 10.0 kWh — roughly what a fridge uses in a month. That produces 5.6 kg of CO₂.

Key Insights

Open-source weights — can be self-hosted on infrastructure you control

What does your Qwen 3.5 72B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Qwen 3.5 72B.

Calculate My Compute

Frequently Asked Questions

How much energy does Qwen 3.5 72B use per query?

Each Qwen 3.5 72B query consumes approximately 1.1 Wh of energy. This is 4x more than a traditional Google search (~0.3 Wh).

What is Qwen 3.5 72B's carbon footprint?

Based on the carbon intensity of Alibaba Cloud (China) / self-hosted, each query produces approximately 0.61 g of CO2. The grid in this region has a carbon intensity of 550 g CO2/kWh with 30% renewable energy.

How much water does Qwen 3.5 72B use?

Each query consumes approximately 4 mL of water, primarily used for cooling the data centers that process the request.

How does Qwen 3.5 72B compare to a Google search?

A Qwen 3.5 72B query uses 4x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Qwen 3.5 72B uses 1.1 Wh.

Technical Details

Architecture

Dense Transformer with hybrid thinking/non-thinking

Parameters

72B

Context window

262,000 tokens

Release date

2026-02-15

Open source

Yes

Training data cutoff

2026-01