Microsoft Joins the Local AI Push
Watching the Microsoft Windows and Surface laptop event turned out to be a lot more interesting than normal. Microsoft is clearly going all in on local AI running on your machine and working with cloud models only when it needs to use them. Microsoft Blog https://blogs.windows.com/windowsexperience/2026/10/07/building-windows-for-hybrid-intelligence/ Full Live Event: https://www.youtube.com/live/ilmBGeGldrI?si=efkp_hpmAV8rI4Ka 2nd Channel: https://www.youtube.com/channel/UCUF7WtR4JpVbQqcQGrLeADw Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 01:17 Hybrid intelligence 01:29 How the Copilot router picks local or cloud 04:21 MAI Code 1.1 Flash at 3 bits 05:07 A New Nemotron at 2 bits 05:37 DeepSeek V4 Flash at 1.6 bits 07:19 The memory cost of 256K context 08:21 llama.cpp inside Windows ML 10:02 MXC: sandboxing agents in Windows 11:00 Surface Laptop Ultra and RTX Spark 11:25 Specs and pricing 11:58 Desktop and DGX Station for Windows 12:15 Why this matters for local AI
