Simon is a Computer Science BSc graduate who has been writing about technology since 2014, and using Windows machines since 3.1. After working for an indie game studio and acting as the family's go-to technician for all computer issues, he found his passion for writing and decided to use his skill set to write about all things tech.
Since beginning his writing career, he has written for many different publications such as WorldStart, Listverse, and MakeTechEasier. However, after finding his home at MakeUseOf in February 2019, he would eventually move on to its sister site, XDA, to bring the latest and greatest in Windows, Linux, and DIY electronics.
Sign in to your XDA account
Summary
- RTX Spark Arm Windows laptops launched Oct. 16 across major OEMs for powerful local AI processing.
- Underdog app runs local models with the Husky inference engine, with no cloud required; the data stays on your laptop.
- Speculative decoding (MTP) tasks speed up by ~1.4x on RTX Pro 6000 Blackwell via llama.cpp, and some models get day-zero support.
Back in mid-October, Nvidia's RTX Spark devices hit the shelves. These are powerful Arm-based System-on-Chip devices that run Windows, designed specifically to be processing powerhouses, especially for local LLM models. Now, Nvidia has revealed what to expect from these shiny new RTX Spark devices, including a new app called Underdog.
Running models on an RTX Spark gets even easier with Underdog
It's a match made in heaven
As announced on the Nvidia blog, the company starts things off by discussing its new range, RTX Spark. These laptops were released on October 16th, and Nvidia says you can grab one in ASUS, Dell, HP, Lenovo, Microsoft, and MSI flavors, with Acer in the works.
A big reason why someone may want to drop money on a new RTX Spark is for the on-board AI capabilities. To help with that, Nvidia announced that it has released its new Underdog app that's ready to download. This app uses a Husky model-specific inference engine to run local AI models on your system, and because it never needs to speak to the cloud, all of your data stays safe on your laptop.
There's also some good news for people who love llama.cpp. Nvidia announced that there has been "new speculative decoding support with MTP for Qwen 3.8 Flash Next," which allows end-to-end agentic tasks to speed up by 1.4x times when they're running off an RTX Pro 6000 Blackwell.
Nvidia also took the time to announce that these models are getting day-zero support: Nemotron Bolt E4B 4B, GLM,
DeepSeek, Qwen, MiniMax, and FLUX 3 Klein diffusion model. This means they should work with your setup the day they release, so there's no need to wait around for Nvidia to publish support for them.