Skip to content
 
 

Repository files navigation

Track Sustainability

Estimation and Simulation of the CO₂ Impact of LLM (Large Language Model) Queries

Hackathon IBM x ESILV


🎯 Project Objective

As the use of generative AI continues to grow, its environmental impact has become a key concern.
Track Sustainability provides a solution to measure and visualize the carbon footprint of a query executed on a Large Language Model (LLM).

The goal is to raise awareness among users about the energy consumption and CO₂ emissions associated with AI usage, while offering clear and relatable comparisons (e.g., equivalent kilometers by car, duration of lighting a bulb, etc.).


🧠 Project Overview

We are developing an interactive web application that looks just like a standard LLM chat interface.

When a user submits a request:

  1. The request is processed by a pre-trained model capable of estimating the energy cost of handling the query.
  2. This estimated cost is converted into CO₂ emissions.
  3. The app displays a visual comparison to help the user understand the impact of their query.

The project leverages the WatsonX platform for model interaction, computation, and performance evaluation.


🛠️ Technologies Used

Technology / Tool Purpose
WatsonX Runtime environment and model analysis
Machine Learning / Deep Learning Estimation of computational and environmental cost
Web Application (Frontend + Backend) User interface and application logic
Data Visualization Tools Clear and intuitive representation of CO₂ impact

👥 Team Members

Project developed as part of the IBM x ESILV Hackathon by:

  • Paul Ranc
  • Héloïse Roméo
  • Natalia Gerard
  • Alexis Denneulin
  • Valentin Rech
  • Valentin Templé

🚀 Vision

Our ambition is to create a reference tool for environmental awareness in AI usage.
Understanding the impact is the first step toward responsible innovation.


About

No description, website, or topics provided.

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages