![[Webinar Alert] Intel is Bringing GenAI to Life on AI PCs](/cdn-cgi/image/width=1600,quality=60,format=auto,fit=scale-down/https://gspoceeuwjazjpplxtxe.supabase.co/storage/v1/object/public/imported-images/1768567704439-c8ffdf4c-bd76-46b7-b204-14982a959277-824qx8u.webp)
Key takeaways
- Join the Intel webinar on deploying LLMs on AI PCs using OpenVINO toolkit.
- Learn techniques like model quantization and runtime optimization for efficient AI performance.
- Discover how AI can run privately and efficiently on personal hardware.
- Register for the session scheduled on May 22, 2025, from 5-6 PM IST.
- Gain insights from AI expert Anisha Udayakumar to enhance your AI projects.
Generative AI is reshaping the way we build and interact with technology, powering everything from intelligent chatbots to advanced image generation tools. But the real magic begins when these models can run efficiently and privately on personal hardware, making AI models as personal as possible.
That’s precisely what the upcoming webinar hosted by AIM in partnership with Intel aims to explore.
Titled “The Optimized AI Stack: Bringing GenAI to Life on AI PCs,” this session will walk developers through the end-to-end deployment of LLMs on AI PCs using a finely tuned mix of CPU, GPU, and NPU acceleration—all powered by the Intel’s OpenVINO toolkit.
Date: 22nd May 2025
Time: 5 – 6 PM IST
Register here
Led by Anisha Udayakumar, AI Software Evangelist at Intel India, the webinar will cover key techniques such as model quantisation, runtime optimisation, and real-time inference improvements. She is dedicated to empowering developers by showcasing how OpenVINO enhances AI projects, fostering innovation and deeper adoption within the community.
Formerly an Innovation Consultant at a leading IT firm, Udayakumar guided business leaders in adopting next-gen technologies like AI and 5G to address complex challenges. With expertise in computer vision, she has delivered solutions that supported a global retail client’s sustainability goals.
Why Should You Attend?
The Webinar is a must-attend session for AI and ML developers seeking to build fast, scalable, and private generative AI applications that rely less on cloud infrastructure. This is an increasingly popular field, as the size of the models has been decreasing over the years and is now capable of being fitted on edge devices.
In this webinar, Udayakumar will provide real-world examples, ranging from Deepseek and Meta’s Llama to OpenAI’s Whisper and Stable Diffusion, illustrating how to run these models on-device seamlessly. It will empower developers not only to learn how to code on AI models, but also to build such tools themselves.
Date: 22nd May 2025
Time: 5 – 6 PM IST
Register here
Join us to explore how the right software stack can bring GenAI to life, right on your PC.
