Models & Labs
Windows Optimized for Nvidia RTX Spark
The Verge AIhigh confidence
Why it matters
- →Windows Store now serves as a centralized hub for installing and managing local AI agents on Arm hardware.
- →Prism emulator optimizations make x64 app compatibility viable on high-performance Arm laptops for the first time.
- →Unified memory tuning allows large local models to run alongside gaming without crashing the system.
Microsoft and Nvidia have finalized deep software optimizations for the new RTX Spark laptop platform, which utilizes Arm-based CPUs and Blackwell GPUs with unified memory. Key updates include a streamlined Windows Store experience for installing local AI agents like Hermes and Perplexity, alongside significant improvements to the Prism emulator to support x64 applications on the new hardware. Microsoft has also tuned memory management to balance large model inference with system responsiveness, allowing users to manually allocate resources between CPU and GPU tasks. While Copilot Plus features like Recall are delayed until later this year, the current software stack enables playable gaming performance for titles such as Fortnite and Counter-Strike 2 through optimized emulation.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1NVIDIA Unveils Nemotron 3.5 Lightning
Lev Selector · August 14, 2026 · Background
- 2NVIDIA Unveils RTX Spark for Next-Gen Gaming
NVIDIA Blog · August 25, 2026 · Related
- 3Nvidia Unveils AI-Powered RTX Spark PCs
WIRED AI · September 3, 2026 · Related
- 4Perplexity Portable Computer Launches on Windows with NVIDIA RTX
NVIDIA Blog · September 14, 2026 · Related
- 5Microsoft Surface RTX Spark Dev Box Preorders Open
The Verge AI · October 7, 2026 · Related
- 6Microsoft Surface Laptop Ultra launches with Nvidia RTX Spark
The Verge AI · October 7, 2026 · Same story
- 7Microsoft launches Nvidia Spark AI PCs with agent-ready Windows 11
TechCrunch AI · October 7, 2026 · Related
- 8Microsoft Unveils New Maia 300 Chip
The AI Daily Brief · October 13, 2026 · Background
What happened next
- 9Nvidia releases open Nemotron models for agents and PCs
TechCrunch AI · October 19, 2026 · Background
More from The Verge AI
© The Verge AICoding Toolscoding
DIY Muse Gadget proves Meta's hardware is just a dev kit
Meta’s Muse Charm isn’t a finished product; it’s an invitation to hack. A non-coder used Claude Code to transform a $50 Waveshare ESP32-S3 dev board into a fully functional AI companion, adding ElevenLabs voice synthesis, custom Tamagotchi-style minigames, and remote camera controls that Meta’s official firmware lacks. This reveals a critical truth: the value of Meta’s new hardware ecosystem lies not in its out-of-the-box utility, but in its open-source API allowing anyone to rewrite the experience. The gap between Meta’s polished demo and the actual user reality is bridged entirely by third-party AI coding tools.
The Verge AI
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© The Verge AIMarket & Regulationbusiness
Altman argues cloud RAM over local inference
Sam Altman is pushing back against the local AI trend, arguing that hoarding DRAM in personal devices is a global waste during a severe supply crunch. He points out that consumer hardware sits idle most of the time, whereas cloud data centers achieve the high utilization rates needed to justify the billions invested by players like OpenAI and Stargate. This isn't just an opinion; it's a defense of the centralized infrastructure model against the growing open-source movement. The real-world impact is visible in the locked-up supply from Samsung and SK Hynix, which drives up costs for everyone else.
The Verge AI
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe
© Lev SelectorModels & Labsmodels
Google Gemini 4 Carbon Leads LM Arena Leaderboard
Google's new model, Gemini 4 Carbon, has taken the top spot on the LMSYS Chatbot Arena leaderboard.
Lev Selector