Text / Chat

GPT-OSS 120B Environmental Impact

StandardEstimated

OpenAI's first open-weight model — Apache 2.0, near o4-mini reasoning

Architecture
Dense Transformer (open-weight)
Parameters
120B
Context
128,000 tokens
Provider
OpenAI
1.8 Wh
Energy per query
0.79 g
CO₂ per query
7 mL
Water per query
6x more than
vs Google search

Energy per query

1.8 Wh

6x more than a Google search (0.3 Wh)

CO2 per query

0.79 g

Global Average grid (475 gCO₂/kWh)

Water per query

7 mL

~154 queries to fill 1 litre

Processing location

Self-hosted (varies)

Provider

OpenAI

Category

Text / Chat

Grid carbon intensity

475 g CO2/kWh (27% renewable)

How does GPT-OSS 120B compare?

Ranked #85 of 152 models by energy per query

0 Wh0.45 Wh0.9 Wh1.35 Wh1.8 WhLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 NanoGPT-OSS 120BGoogle search (0.3 Wh)

Detailed Breakdown

Energy Consumption

GPT-OSS 120B is OpenAI's first open-weight model (Apache 2.0), achieving near-parity with o4-mini on reasoning benchmarks. At ~1.8 Wh per query, it runs on a single 80GB GPU. Its release marked a major strategic shift for OpenAI toward open-source. Hugely popular on Hugging Face and Ollama.

Power Source & Carbon

Fully open-weight (Apache 2.0). Self-hostable on a single GPU, enabling deployment on low-carbon infrastructure.

Water Usage

At ~6.5 mL per query on cloud. Zero when self-hosted on consumer hardware.

About GPT-OSS 120B

GPT-OSS 120B is an open-source text and chat model from OpenAI, released in August 7, 2025, that runs below the category average for energy consumption at 1.8 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 120B parameters, it openai's first open-weight model — apache 2.0, near o4-mini reasoning.

These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for GPT-OSS 120B. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

GPT-OSS 120B in Context

16.4 kWh
per year

Your yearly GPT-OSS 120B footprint

At 25 queries per day, your annual GPT-OSS 120B usage consumes 16.4 kWh — roughly what a fridge uses in a month. That produces 7.2 kg of CO₂.

Key Insights

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

What does your GPT-OSS 120B usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use GPT-OSS 120B.

Calculate My Compute

Frequently Asked Questions

How much energy does GPT-OSS 120B use per query?

Each GPT-OSS 120B query consumes approximately 1.8 Wh of energy. This is 6x more than a traditional Google search (~0.3 Wh).

What is GPT-OSS 120B's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 0.79 g of CO2. The grid in this region has a carbon intensity of 475 g CO2/kWh with 27% renewable energy.

How much water does GPT-OSS 120B use?

Each query consumes approximately 7 mL of water, primarily used for cooling the data centers that process the request.

How does GPT-OSS 120B compare to a Google search?

A GPT-OSS 120B query uses 6x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while GPT-OSS 120B uses 1.8 Wh.

Technical Details

Architecture

Dense Transformer (open-weight)

Parameters

120B

Context window

128,000 tokens

Release date

2025-08-07

Open source

Yes

Training data cutoff

2025-06