Text / Chat

GLM-4 Environmental Impact

StandardEstimated

China's leading open-source bilingual model family

Architecture
General Language Model (autoregressive)
Context
128,000 tokens
Provider
Zhipu AI
0.90 Wh
Energy per query
0.50 g
CO₂ per query
3 mL
Water per query
3x more than
vs Google search

Energy per query

0.90 Wh

3x more than a Google search (0.3 Wh)

CO2 per query

0.50 g

China grid (550 gCO₂/kWh)

Water per query

3 mL

~303 queries to fill 1 litre

Processing location

Zhipu AI Cloud (China)

Provider

Zhipu AI

Category

Text / Chat

Grid carbon intensity

550 g CO2/kWh (30% renewable)

How does GLM-4 compare?

Ranked #49 of 152 models by energy per query

0 Wh0.25 Wh0.5 Wh0.75 Wh1 WhLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 NanoGLM-4Google search (0.3 Wh)

Detailed Breakdown

Energy Consumption

GLM-4 is a competitive bilingual (Chinese/English) model at ~0.9 Wh per query. The open-source ChatGLM series has been widely deployed in Chinese enterprises and research institutions.

Power Source & Carbon

Available both as open-source (self-hosted) and via Zhipu's API running on Chinese data centres.

Water Usage

At ~3.3 mL per query when using the hosted API. Self-hosted deployments vary by location.

About GLM-4

GLM-4 is an open-source text and chat model from Zhipu AI, released in January 16, 2024, that runs well below the category average for energy consumption at 0.90 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. It china's leading open-source bilingual model family.

These figures are estimates derived from hardware specifications and API benchmarks — Zhipu AI has not published official energy data for GLM-4. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

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

Zhipu AI GLM Family

How energy efficiency has evolved across versions.

What does your GLM-4 usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use GLM-4.

Calculate My Compute

Frequently Asked Questions

How much energy does GLM-4 use per query?

Each GLM-4 query consumes approximately 0.90 Wh of energy. This is 3x more than a traditional Google search (~0.3 Wh).

What is GLM-4's carbon footprint?

Based on the carbon intensity of Zhipu AI Cloud (China), each query produces approximately 0.50 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 GLM-4 use?

Each query consumes approximately 3 mL of water, primarily used for cooling the data centers that process the request.

How does GLM-4 compare to a Google search?

A GLM-4 query uses 3x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while GLM-4 uses 0.90 Wh.

Technical Details

Architecture

General Language Model (autoregressive)

Context window

128,000 tokens

Release date

2024-01-16

Open source

Yes

Training data cutoff

2024-01