How to run DeepSeek models on Windows on Snapdragon – LM Studio tutorial

Co-written with Li He, Srinivasa Deevi, Hongqiang Wang, Sai Gayatri Gampa.

DeepSeek-R1 is an open-source reasoning model developed by DeepSeek to handle tasks requiring logical inference, mathematical problem-solving and real-time decision making. One of its standout features is the ability to trace its logic, which makes it easier to understand and, if necessary, challenge its output.

This transparency is particularly valuable in fields where explainable outcomes are crucial, such as research and complex decision making.

AI distillation is a process that creates smaller, more efficient models from larger ones, retaining much of their reasoning power while reducing computational demands. DeepSeek has applied this technique to develop a suite of distilled models from R1, using Qwen and Llama architectures. That allows users to take advantage of the capabilities of DeepSeek-R1 on standard laptops.

Developers have a few options to run their AI models on Windows on Snapdragon. One of the most popular options is to leverage LLM platforms like LM Studio. LM Studio stands out due to its user-friendly interface, robust performance, and seamless integration with popular AI models. It supports a wide range of models making it highly versatile.

Additionally, LM Studio allows developers to run models locally, ensuring data privacy and reducing dependency on internet connectivity. Its ability to work offline and its compatibility makes it an ideal choice for developers looking to experiment with AI models efficiently.

The platform has also received positive feedback from prominent figures in the tech community, further solidifying its reputation as a reliable and effective tool for AI development.

This tutorial shows you how to run DeepSeek-R1 models on Windows on Snapdragon CPU using LM Studio. You can run the steps below on Snapdragon X Series laptops.

Running on CPU – LM Studio how to guide

1. Visit the LM Studio website. Open your browser and go to https://lmstudio.ai. 

2. Download and install. Download the LM Studio for Windows (arm64) installer. Follow the on-screen instructions to complete the installation and launch the application.

3. Initialize your model. From the onboarding screen, select your LLM model and wait for it to download:

4. Start using the application. Once the download is complete, you can load the model and begin using the chat application based on the selected LLM model:

5. Switch models. You can select a different model from the dropdown menu at the top; for example, DeepSeek R1 Distilled (Qwen 7B), as shown below:

6. Monitor performance. Open the Windows Task Manager to see the model running locally (using CPU) on your device:

Next steps

We’ll have more details shortly about running on NPU.

Meanwhile, Microsoft is bringing NPU-optimized versions of DeepSeek-R1 directly to Copilot+ PCs, starting with Qualcomm Snapdragon X Series devices. The company also announced that the distilled DeepSeek R1 models, optimized using ONNX, are now available on Snapdragon-powered Copilot+ PCs. These models offer a time to first token of less than 70 ms for short prompts (<64 tokens) and a throughput rate of 25-40 tokens/s, with longer responses achieving higher throughput. Get started today by downloading the AI Toolkit extension in VS Code.

Want to find out more about DeepSeek on Windows on Snapdragon? Join our Developer Discord for more insights and real-time conversations with fellow developers and our technical experts.