Microsoft is bringing NPU-optimized variations of DeepSeek R1 to Copilot+ PCs.
- DeepSeek R1 is first coming to Qualcomm Snapdragon X-powered gadgets, followed by Intel and AMD AI chipsets.
- The DeepSeek-R1-Distill-Qwen-1.5 B design is being contributed to the Microsoft AI Toolkit.


Microsoft has announced that it's bringing NPU-optimized versions of DeepSeek R1 to Copilot+ PCs. The business will likewise integrate the DeepSeek-R1-Distill-Qwen-1.5 B model into its Microsoft AI Toolkit for designers, with the 7B and 14B versions set to follow.


In a recent post, Microsoft announced that DeepSeek R1 designs will initially be available on Qualcomm Snapdragon X-powered PCs, followed by Intel Core Ultra 200V laptops and AMD AI chipsets. This release will allow designers to build AI-powered apps that run in your area on suitable Copilot+ PCs.


"The enhanced DeepSeek designs for the NPU take benefit of numerous of the crucial knowings and techniques from that effort, including how we separate out the different parts of the design to drive the finest tradeoffs between efficiency and performance, low bit rate quantization and mapping transformers to the NPU," Microsoft explained.


Microsoft has laid out the hardware requirements for running these AI designs on Windows 11 gadgets. To certify, a PC needs to have a Neural Processing Unit (NPU) with at least 40 TOPS (trillion operations per second), 16GB of RAM, and 256GB of storage. This suggests that PCs with old NPUs won't be able to run these models locally.


How to run DeepSeek R1 on Windows 11 Copilot+ PCs?


To begin with DeepSeek on a Copilot+ PC, designers will require to create an Azure account on Microsoft's website. Now, launch Azure AI Foundry and then look for DeepSeek R1. Select the "Check out model" option, click Deploy, and after that click "Deploy" again in the pop-up window. The Chat Playground option will appear, and designers can start explore DeepSeek R1 locally on their Copilot+ PCs.


Microsoft has actually likewise revealed that it's making the open-source DeepSeek R1 LLM offered for developers through Azure AI Foundry and GitHub. "Among the key benefits of utilizing DeepSeek R1 or any other model on Azure AI Foundry is the speed at which designers can experiment, repeat, and incorporate AI into their workflows. With integrated design assessment tools, they can quickly compare outputs, benchmark efficiency, and scale AI-powered applications," stated Asha Sharma, Corporate Vice President, AI Platform.


A new report from the Financial Times exposes that Microsoft is investigating whether Chinese start-up DeepSeek unlawfully utilized OpenAI's data to train its R1 model. This action violates OpenAI's terms of service, and Microsoft prepares to team up with the US federal government to safeguard its AI model.


Microsoft's statement aims to address issues about DeepSeek possibly keeping data on unsecured foreign networks. To mitigate this threat, the company has actually subjected DeepSeek R1 to extensive red teaming and security assessments to decrease the risk of information breaches.