Products / Cloud Computing / Other compute

A distributed platform optimized for high performance computing

We are delighted with this virtuous collaboration between Qarnot and Imagine on several levels. The reduction in compute time that will be achieved thanks to the Qarnot teams is essential to accelerate research, to diagnose sick children, and thus to change the lives of families affected by genetic diseases. These faster, optimized, low-carbon compute are in line with this ambition, as well as with the ambition to reduce our environmental impact as much as possible, in a socially responsible approach.
Pr Stanislas Lyonnet
Director of the Imagine Institute
A deep learning model requires a number of iterations to train the model with different configurations to get the best performance. With Qarnot services, these iterations were fast for us because we could train our model faster and it saved us a lot of time.
KTH Formula Student Team
Being able to deploy computing power according to our needs and benefit from a very practical API is what appealed to us. And last but not least, it reduces the carbon footprint of compute.
Olivier Oldrini
Co-Founder and President of AmpliSIM

compute performed by our customers:

• Machine learning (sales predictions)
• Operations research (delivery path optimization)
• Molecular docking
• Medical research, early disease detection
• Weather forecasting (WRF - Weather Research and Forecasting model)
• Fluid simulations
• Monte Carlo simulations
• Photogrammetry
• 3D image rendering


75% carbon footprint reduction on average

Entrusting your intensive compute to Qarnot, means:
• Accessing a low-carbon infrastructure of several tens of thousands of cores that reuse the IT waste heat
• Drastically reduce the environmental impact of your activity
• Benefiting from a detailed report on each energy expense item
• Know the percentage of savings achieved compared to a conventional infrastructure

An appropriate tool that meets the users’ needs

• Easy integration into an existing architecture thanks to an SDK
• Intuitive API that allows you to launch compute tasks
in a few lines of code or a few clicks
• Real-time monitoring through the user interface dashboard