1.8× less energy than Qwen3.5 35B-A3B.
Qwen3.5 35B-A3B Environmental Impact
Popular mid-size open MoE model for self-hosting
The figures below are for one quick question. A longer chat with follow-ups uses about 0.13 Wh, and an hour or two of agent work about 3.6 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
12% of a Google search.
16% of a Google search.
About 2.6× a drop of water and 3% 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~7,692 queries to fill 1 litre
Where Qwen3.5 35B-A3B sits
#12 of 199 by energy per query. Lighter than 94% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
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
- 3.9 Wh
- Carbon
- 2.1 g
- Water
- 14 mL
A month of 5 chats a day, 5 days a week. The energy is 32% of a phone charge.
Work out your own →- Energy
- 15.6 Wh
- Carbon
- 8.2 g
- Water
- 56 mL
A month of 20 chats a day, 5 days a week. The energy is about 1.3× a phone charge and 14% of a kettle boil.
Work out your own →- Energy
- 77.9 Wh
- Carbon
- 41.1 g
- Water
- 281 mL
A month of 100 chats a day, 5 days a week. The energy is about 6.5× a phone charge and 71% of a kettle boil.
Work out your own →How does Qwen3.5 35B-A3B compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate Qwen3.5 35B-A3B at ~0.036 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). Qwen3.5 35B-A3B activates ~3B of its 35B parameters, which gives ~0.036 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 ~0.55 Wh estimate, which was built on 2025 benchmark figures for older hardware.
Power source & carbon
Fully open-source. Very popular on Ollama and Hugging Face for local deployment.
Water use
At ~0.13 mL per quick question, derived from the energy estimate at the ~3.6 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 Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is an open-source text and chat model from Alibaba, released in February 24, 2026, that runs well below the category average for energy consumption at 0.04 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 35B parameters, it popular mid-size open moe model for self-hosting.
These figures are estimates derived from hardware specifications and API benchmarks — Alibaba has not published official energy data for Qwen3.5 35B-A3B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
Qwen3.5 35B-A3B in context
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
What does your Qwen3.5 35B-A3B usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use Qwen3.5 35B-A3B.
Frequently asked questions
How much energy does Qwen3.5 35B-A3B use per query?
Each Qwen3.5 35B-A3B query consumes approximately 0.04 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).
What is Qwen3.5 35B-A3B's carbon footprint?
Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.02 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 Qwen3.5 35B-A3B use?
Each query consumes approximately 0.13 mL of water, primarily used for cooling the data centers that process the request.
How does Qwen3.5 35B-A3B compare to a Google search?
A Qwen3.5 35B-A3B query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Qwen3.5 35B-A3B uses 0.04 Wh.
Technical details
- Architecture
- Mixture-of-Experts Transformer (35B total, ~3B active) with hybrid thinking
- Parameters
- 35B
- Context window
- 262,000 tokens
- Release date
- 2026-02-24
- Open source
- Yes
- Training data cutoff
- 2026-01