Microsoft Begins Integration of Deepseek R1 Models on Copilot+ PCs

Initially, these models will roll out to Snapdragon X-powered devices, followed by Intel Core Ultra 200V and AMD Ryzen AI 9 PCs. The first release, DeepSeek-R1-Distill-Qwen-1.5B (a 1.5 billion parameter model), will soon be joined by larger 7B and 14B versions. Users can download them from Microsoft’s AI Toolkit.
Microsoft adjusted these models to run efficiently on devices with NPUs. Memory-heavy tasks are handled by the CPU while demanding operations like transformer blocks run on the NPU. Thanks to these optimizations, Microsoft achieved a fast first-token response time of 130ms and a processing speed of 16 tokens per second for short prompts (under 64 tokens). For reference, a “token” is similar to a vowel and usually spans more than one character.
Despite its deep ties to OpenAI, Microsoft isn’t limiting itself to one AI provider. Its Azure Playground already supports GPT models (OpenAI), Llama (Meta), Mistral, and now DeepSeek.
You can run the AI locally. You only need to download the AI Toolkit for VS Code. From there, you can get the model (e.g., “deepseek_r1_1_5” for the 1.5B version). Once installed, click Try in Playground to test how well this distilled version of R1 performs.
“Model distillation,” or “knowledge distillation,” is the process of shrinking a massive AI model (DeepSeek R1 has 671 billion parameters) while keeping as much intelligence as possible. The smaller model (e.g., 1.5B parameters) isn’t as powerful as the full version, but its reduced size allows it to run on regular consumer hardware instead of expensive AI systems.
About the authorMarco Lancaster
Marco has been the HARDWARE & OS EXPERT at Gizchina for over four years, bringing extensive knowledge and a deep passion for technology to the team. His fascination with innovation keeps him constantly exploring the latest trends and advancements in the tech world. Beyond his expertise in hardware, Marco delves into the field of software development, broadening his skills and staying ahead in the ever-evolving industry.
Linkedin Youtube
Marco’s proficiency spans across all types of hardware, making him a go-to authority for in-depth insights and reliable information. He has a particular enthusiasm for the Chinese tech landscape, especially smart devices, which he follows with keen interest. As a self-proclaimed tech addict, Marco lives and breathes technology, dedicating himself to understanding and sharing the latest developments with Gizchina’s audience.
Marco is not only an expert in hardware and software but also a passionate gamer. He enjoys playing games across a wide range of platforms, from nostalgic retro consoles to cutting-edge modern systems. His love for gaming complements his enthusiasm for technology, as he eagerly tests the latest gadgets, and hardware to stay on top of emerging trends and innovations.
As a Continuous Student of computer science, and full stack developer, Marco has a great knowledge in this wonderful world of technology and internet.