[WiMLDS x MLOps Paris] How to make AI models faster, cheaper & greener.

⚠️⚠️⚠️ Mandatory registration on Eventbrite via this link ⚠️⚠️⚠️

[WiMLDS Paris x MLOps Paris] How to make AI models faster, cheaper & greener.
Welcome to this exclusive collaboration between Women in Machine Learning & Data Science Paris and MLOps Paris.
Whether you are a seasoned professional in operationalizing ML systems or just getting started with Machine Learning in production, you are invited to join this limited event, attend a talk and network with other professionals in the field.

About the talk:
AI models become more complex, the cost of inference—both in terms of computation and energy—continues to rise. In this talk, Minette Kaunismäki will explore how combining compression techniques such as quantisation, pruning, caching, and distillation can significantly optimise model performance during inference. By applying these methods, combining compression enables reductions in model size and computational load while maintaining quality, thereby making AI more accessible and environmentally sustainable.

The talk and Q&A will be in English.

⚠️⚠️⚠️ Mandatory registration on Eventbrite via this link ⚠️⚠️⚠️

⏰ Planning

• 18h45 - 19h15 : Accueil & introduction 👋
• 19h15 - 20h15 : Talk 🎤
• 20h15 - 22h00: Cocktail & échanges 🥂

🎙 Speakers
Minette Kaunismäki is Developer Advocate @ Pruna.ai

🙌 Sponsors et entreprises participantes

**Vestiaire Collective **is a C2C global platform for buying and selling pre-owned luxury and premium fashion. Founded in Paris in 2009, Vestiaire Collective brings together a community of millions of fashion lovers across more than 80 countries. The company is committed to transforming the fashion industry by promoting circularity, sustainability, and more responsible consumption—powered by technology, trust, and a strong human community.
**[Pruna.ai ](https://www.pruna.ai/ "https://www.pruna.ai/")**is a European AI startup and AI optimization engine focused on making machine learning models faster, cheaper, smaller, and greener — especially for production inference at scale. It’s both a platform and a framework/toolkit that helps developers and ML teams optimize existing AI models with minimal overhead.

🤩 Audience
Cet évènement est destiné aux professionels de la data et de l'algorithmique et qui souhaitent pousser plus loin les efforts d'industrialisation dans leurs organisations : data scientists, data engineers, software et devops engineers, data project/product managers, product designers, etc.

👋 Contact
Pour toute question ou information, merci de contacter [florent@nibble.ai](http://mailto:florent@nibble.ai)