Uploaded October 2025 | Updated September 2026, 2 weeks ago
Panther Lake represents the next chapter for Intel AI PCs. In this episode of Talking Tech, we look back on the development of hardware and software to support executing AI workloads locally on client PCs. Learn about how our XPU strategy combines the CPU with NPU and GPU accelerators to provide a diverse array of engines tuned for different types of AI workloads, how models derived from datacenters are optimized for local inference, how we work closely with OS and software providers to enable compelling user experiences, and what OpenVINO brings to the table along with Windows ML.
Follow along for more information about Panther Lake: youtube.com/playlist?list=PL8t1FdN2Tj3a8dkQruuF8ZytUaxE4EwQQ
See Panther Lake in action at Computex: youtu.be/GuQQ9jXCQL4?si=lJjutRvlfznIq2Hm
Chapters:
00:00 – Introduction
01:38 – How XPU hardware meets software needs
07:16 – Hardware and software co-optimization
08:31 – How we move models from datacenter to PC
12:24 – Developing OpenVINO
14:24 – Working with Windows ML
16:38 – Engaging the OS and software ecosystem
20:45 – The importance of local inferencing
24:54 – The pace of innovation
26:04 – Agentic AI
29:19 – Looking ahead
About Intel Technology: Intel has always been at the forefront of developing exciting new technology for business and consumers including emerging technologies, data center servers, business transformation, memory and storage, security, and graphics. The Intel Technology YouTube channel is a place to learn tips and tricks, get the latest news, and watch product demos from both Intel and our many partners across multiple fields.
Connect with Intel Technology:
Visit Intel Technologies WEBSITE: intel.ly/IntelTechnologies
Panther Lake represents the next chapter for Intel AI PCs. In this episode of Talking Tech, we look back on the development of hardware and software to support executing AI workloads locally on client PCs. Learn about how our XPU strategy combines the CPU with NPU and GPU accelerators to provide a diverse array of engines tuned for different types of AI workloads, how models derived from datacenters are optimized for local inference, how we work closely with OS and software providers to enable compelling user experiences, and what OpenVINO brings to the table along with Windows ML.
Follow along for more information about Panther Lake: youtube.com/playlist?list=PL8t1FdN2Tj3a8dkQruuF8ZytUaxE4EwQQ
See Panther Lake in action at Computex: youtu.be/GuQQ9jXCQL4?si=lJjutRvlfznIq2Hm
Chapters:
00:00 – Introduction
01:38 – How XPU hardware meets software needs
07:16 – Hardware and software co-optimization
08:31 – How we move models from datacenter to PC
12:24 – Developing OpenVINO
14:24 – Working with Windows ML
16:38 – Engaging the OS and software ecosystem
20:45 – The importance of local inferencing
24:54 – The pace of innovation
26:04 – Agentic AI
29:19 – Looking ahead
About Intel Technology: Intel has always been at the forefront of developing exciting new technology for business and consumers including emerging technologies, data center servers, business transformation, memory and storage, security, and graphics. The Intel Technology YouTube channel is a place to learn tips and tricks, get the latest news, and watch product demos from both Intel and our many partners across multiple fields.
Connect with Intel Technology:
Visit Intel Technologies WEBSITE: intel.ly/IntelTechnologies
