Edge AI for Beginners : Getting Started with Foundry Local
In Module 08 of the EdgeAI for Beginners course, Microsoft introduces Foundry Local a toolkit that helps you deploy and test Small Language Models (SLMs) completely offline. In this blog, I’ll share how I installed Foundry Local, ran the Phi-3.5-mini model on my windows laptop, and what I learned through the process. What Is Foundry Local? Foundry Local allows developers to run AI models locally on their own hardware. It supports text generation, summarization, and code completion — all without sending data to the cloud. Unlike cloud-based systems, everything happens on your computer, so your data never leaves your device. Prerequisites Before starting, make sure you have: Windows 10 or 11 Python 3.10 or newer Git Internet connection (for the first-time model download) Foundry Local installed Step 1 — Verify Installation After installing Foundry Local, open Command Prompt and type: foundry --version If you see a version number, Foundry Local is installed correctly. Step 2 — Start the Service Start the Foundry Local service using: foundry service start You should see a confirmation message that the service is running. Step 3 — List Available Models To view the models supported by your system, run: foundry model list You’ll get a list of locally available SLMs. Here’s what I saw on my machine: Note: Model availability depends on your device’s hardware. For most laptops, phi-3.5-mini works smoothly on CPU. Step 4 — Run the Phi-3.5 Model Now let’s start chatting with the model: foundry model run phi-3.5-mini-instruct-generic-cpu:1 Once it loads, you’ll enter an interactive chat mode. Try a simple prompt: Hello! What can you do? The model replies instantly — right from your laptop, no cloud needed. To exit, type: /exit How It Works Foundry Local loads the model weights from your device and performs inference locally.This means text generation happens using your CPU (or GPU, if available). The result: complete privacy, no internet dependency, and instant responses. Benefits for Students For students beginning their journey in AI, Foundry Local offers several key advantages: No need for high-end GPUs or expensive cloud subscriptions. Easy setup for experimenting with multiple models. Perfect for class assignments, AI workshops, and offline learning sessions. Promotes a deeper understanding of model behavior by allowing step-by-step local interaction. These factors make Foundry Local a practical choice for learning environments, especially in universities and research institutions where accessibility and affordability are important. Why Use Foundry Local Running models locally offers several practical benefits compared to using AI Foundry in the cloud. With Foundry Local, you do not need an internet connection, and all computations happen on your personal machine. This makes it faster for small models and more private since your data never leaves your device. In contrast, AI Foundry runs entirely on the cloud, requiring internet access and charging based on usage. For students and developers, Foundry Local is ideal for quick experiments, offline testing, and understanding how models behave in real-time. On the other hand, AI Foundry is better suited for large-scale or production-level scenarios where models need to be deployed at scale. In summary, Foundry Local provides a flexible and affordable environment for hands-on learning, especially when working with smaller models such as Phi-3, Qwen2.5, or TinyLlama. It allows you to experiment freely, learn efficiently, and better understand the fundamentals of Edge AI development. Optional: Restart Later Next time you open your laptop, you don’t have to reinstall anything. Just run these two commands again: foundry service start foundry model run phi-3.5-mini-instruct-generic-cpu:1 What I Learned Following the EdgeAI for Beginners Study Guide helped me understand: How edge AI applications work How small models like Phi 3.5 can run on a local machine How to test prompts and build chat apps with zero cloud usage Conclusion Running the Phi-3.5-mini model locally with Foundry Localgave me hands-on insight into edge AI. It’s an easy, private, and cost-free way to explore generative AI development. If you’re new to Edge AI, start with the EdgeAI for Beginners course and follow its Study Guide to get comfortable with local inference and small language models. Resources: EdgeAI for Beginners GitHub Repo Foundry Local Official Site Phi Model LinkStep-by-step: Integrate Ollama Web UI to use Azure Open AI API with LiteLLM Proxy
Introductions Ollama WebUI is a streamlined interface for deploying and interacting with open-source large language models (LLMs) like Llama 3 and Mistral, enabling users to manage models, test them via a ChatGPT-like chat environment, and integrate them into applications through Ollama’s local API. While it excels for self-hosted models on platforms like Azure VMs, it does not natively support Azure OpenAI API endpoints—OpenAI’s proprietary models (e.g., GPT-4) remain accessible only through OpenAI’s managed API. However, tools like LiteLLM bridge this gap, allowing developers to combine Ollama-hosted models with OpenAI’s API in hybrid workflows, while maintaining compliance and cost-efficiency. This setup empowers users to leverage both self-managed open-source models and cloud-based AI services. Problem Statement As of February 2025, Ollama WebUI, still do not support Azure Open AI API. The Ollama Web UI only support self-hosted Ollama API and managed OpenAI API service (PaaS). This will be an issue if users want to use Open AI models they already deployed on Azure AI Foundry. Objective To integrate Azure OpenAI API via LiteLLM proxy into with Ollama Web UI. LiteLLM translates Azure AI API requests into OpenAI-style requests on Ollama Web UI allowing users to use OpenAI models deployed on Azure AI Foundry. If you haven’t hosted Ollama WebUI already, follow my other step-by-step guide to host Ollama WebUI on Azure. Proceed to the next step if you have Ollama WebUI deployed already. Step 1: Deploy OpenAI models on Azure Foundry. If you haven’t created an Azure AI Hub already, search for Azure AI Foundry on Azure, and click on the “+ Create” button > Hub. Fill out all the empty fields with the appropriate configuration and click on “Create”. After the Azure AI Hub is successfully deployed, click on the deployed resources and launch the Azure AI Foundry service. To deploy new models on Azure AI Foundry, find the “Models + Endpoints” section on the left hand side and click on “+ Deploy Model” button > “Deploy base model” A popup will appear, and you can choose which models to deploy on Azure AI Foundry. Please note that the o-series models are only available to select customers at the moment. You can request access to the o-series models by completing this request access form, and wait until Microsoft approves the access request. Click on “Confirm” and another popup will emerge. Now name the deployment and click on “Deploy” to deploy the model. Wait a few moments for the model to deploy. Once it successfully deployed, please save the “Target URI” and the API Key. Step 2: Deploy LiteLLM Proxy via Docker Container Before pulling the LiteLLM Image into the host environment, create a file named “litellm_config.yaml” and list down the models you deployed on Azure AI Foundry, along with the API endpoints and keys. Replace "API_Endpoint" and "API_Key" with “Target URI” and “Key” found from Azure AI Foundry respectively. Template for the “litellm_config.yaml” file. model_list: - model_name: [model_name] litellm_params: model: azure/[model_name_on_azure] api_base: "[API_ENDPOINT/Target_URI]" api_key: "[API_Key]" api_version: "[API_Version]" Tips: You can find the API version info at the end of the Target URI of the model's endpoint: Sample Endpoint - https://example.openai.azure.com/openai/deployments/o1-mini/chat/completions?api-version=2024-08-01-preview Run the docker command below to start LiteLLM Proxy with the correct settings: docker run -d \ -v $(pwd)/litellm_config.yaml:/app/config.yaml \ -p 4000:4000 \ --name litellm-proxy-v1 \ --restart always \ ghcr.io/berriai/litellm:main-latest \ --config /app/config.yaml --detailed_debug Make sure to run the docker command inside the directory where you created the “litellm_config.yaml” file just now. The port used to listen for LiteLLM Proxy traffic is port 4000. Now that LiteLLM proxy had been deployed on port 4000, lets change the OpenAI API settings on Ollama WebUI. Navigate to Ollama WebUI’s Admin Panel settings > Settings > Connections > Under the OpenAI API section, write http://127.0.0.1:4000 as the API endpoint and set any key (You must write anything to make it work!). Click on “Save” button to reflect the changes. Refresh the browser and you should be able to see the AI models deployed on the Azure AI Foundry listed in the Ollama WebUI. Now let’s test the chat completion + Web Search capability using the "o1-mini" model on Ollama WebUI. Conclusion Hosting Ollama WebUI on an Azure VM and integrating it with OpenAI’s API via LiteLLM offers a powerful, flexible approach to AI deployment, combining the cost-efficiency of open-source models with the advanced capabilities of managed cloud services. While Ollama itself doesn’t support Azure OpenAI endpoints, the hybrid architecture empowers IT teams to balance data privacy (via self-hosted models on Azure AI Foundry) and cutting-edge performance (using Azure OpenAI API), all within Azure’s scalable ecosystem. This guide covers every step required to deploy your OpenAI models on Azure AI Foundry, set up the required resources, deploy LiteLLM Proxy on your host machine and configure Ollama WebUI to support Azure AI endpoints. You can test and improve your AI model even more with the Ollama WebUI interface with Web Search, Text-to-Image Generation, etc. all in one place.Showcasing Phi-4-Reasoning: A Game-Changer for AI Developers
Showcasing Phi-4-Reasoning: A Game-Changer for AI Developers Introduction Phi-4-Reasoning is a state-of-the-art AI model developed by Microsoft Research, designed to excel in complex reasoning tasks. With its advanced capabilities, Phi-4-Reasoning is a powerful tool for AI developers, enabling them to tackle intricate problems with ease and precision. What is Phi-4-Reasoning? Phi-4-Reasoning is a 14-billion parameter open-weight reasoning model that has been fine-tuned from the Phi-4 model using supervised fine-tuning on a dataset of chain-of-thought traces.. We are also releasing Phi-4-reasoning-plus, a variant enhanced through a short phase of outcome-based reinforcement learning that offers higher performance by generating longer reasoning traces. This model is designed to handle complex reasoning tasks, including mathematical problems, scientific queries, and coding challenges Why Phi-4-reasoning and Phi-4-reasoning-plus Excels Advanced Reasoning Capabilities: Phi-4-Reasoning is trained to generate detailed reasoning chains, making it highly effective in solving complex problems. It leverages additional inference-time compute to enhance its reasoning abilities High-Quality Data Curation: The model's training involved meticulous data curation and the use of high-quality synthetic datasets, allowing it to compete with much larger models Performance: Despite its smaller size, Phi-4-Reasoning outperforms larger models like OpenAI's o1-mini and DeepSeek-R1-Distill-Llama-70B on various benchmarks, including mathematical reasoning and PhD-level science questions Industry Applications: Phi-4-Reasoning is versatile and can be deployed in various industry scenarios, including medicine, where it can be used for reasoning tasks on edge devices Real-World Examples Wordplay Riddle: Phi-4-Reasoning can solve wordplay riddles by recognizing patterns and applying logical reasoning. For example, it deduced that collecting three strawberries would yield 9 r's because the word "strawberry" contains three r's Example 1: How many strawberries for 9 r’s? User: How many strawberries do I need to collect 9 r’s? Phi-4-Reasoning: <think> TRUNCATED </think> It’s a wordplay riddle! Notice that the word “strawberry” has three r’s in it. So if you “collect” three strawberries, you get 3 Å~ 3 = 9 r’s. Thus, you need 3 strawberries. Solving a Riddle: The model can decrypt complex riddles by identifying patterns and performing arithmetic operations. It demonstrated this capability by solving a riddle involving foreign language number-words and reversed number-words. What This Problem Proves: Pattern Recognition: Phi-4-Reasoning demonstrates its ability to identify patterns in words and apply logical reasoning to solve the riddle. Wordplay Understanding: The model showcases its proficiency in understanding and solving wordplay riddles, which require a combination of linguistic knowledge and logical deduction. Efficiency: Phi-4-Reasoning quickly arrives at the correct solution by applying a straightforward multiplication operation, highlighting its efficiency in solving such problems. Example 2: Solving a Riddle User: I will give you a riddle to solve with a few examples, and something to complete at the end What is a likely completion for X that is consistent the with examples above? Phi-4-Reasoning: <think> TRUNCATED </think> We can “decrypt” the riddle by noticing that each line has five parts. In every example the parts are: A “number-word” in a foreign language (or with an extra minus sign), A “first name” (of any nationality), A “reversed number-word” (or two, joined by a hyphen), A “second name”, and A final number. When you “reverse” the third word you get a familiar numberin English: In line 1 “evif” is “five” (5) and the first number is “uno” = 1, and 5 – 1 = 4. In line 2 “neves” is “seven” (7) and “tres” = 3, and 7 – 3 = 4. In line 3 “evlewt” is “twelve” (12) and “drei” = 3, and 12 – 3 = 9. In lines 4 and 5 with two reversed “number-words”: – Line 4: “xis” →“six” (6) and “ytnewt” →“twelve” (12); 6 + 12 = 18, plus 3 = 21. – Line 5: “eerht” → “three” (3) and “ytnewt” → “twelve” (12); 3 + 12 = 15, plus 3 = 18. Now look at the final line: “minus one-point-two Satya eno Bill X” It follows the same five–part format. Notice that “eno” reversed is “one” (1). And the “first number” is “minus onepoint-two” (–1.2). Since for a one–number–word line the rule is: final number = (number from reversed word)−(first number) we compute: final = 1 − (−1.2) = 1 + 1.2 = 2.2 Thus, a likely completion for X is 2.2. Phi-4-Reasoning: Phi-4-Reasoning decrypts the riddle by identifying a pattern in the examples provided. Each line consists of five parts: a number-word in a foreign language, a first name, a reversed number-word, a second name, and a final number. By reversing the third word and performing arithmetic operations, Phi-4-Reasoning determines that the likely completion for X is 2.2 What This Problem Proves: Complex Pattern Recognition: Phi-4-Reasoning excels in recognizing complex patterns involving multiple elements, such as foreign language number-words and reversed number-words. Logical Deduction: The model demonstrates its ability to apply logical deduction to solve the riddle by performing arithmetic operations based on the identified patterns. Versatility: Phi-4-Reasoning showcases its versatility in handling diverse types of riddles and problems, making it a valuable tool for AI developers. Example 3. solve complex graph traversal tasks, such as finding a path through a maze. The maze is represented as an adjacency list, which is a common way to describe graphs in computer science. Each node in the graph (or maze) is connected to other nodes, and the task is to find a valid path from the starting node (node 0) to the destination node Example 3: Solving a maze User: Please solve the maze provided in adjacency list form below, by outputting a valid path from node 0 to node {destination}, in a space-separated list of integers. Adjacency list: {depicted as an image below} Phi-4-Reasoning: <think> TRUNCATED </think> {path depicted as an image below} What This Problem Proves: Graph Traversal Capability: Phi-4-Reasoning can effectively navigate through graphs using algorithms like Depth-First Search (DFS) or Breadth-First Search (BFS). This capability is crucial for solving problems that involve finding paths, cycles, or connectivity in graphs. Logical Reasoning: The model demonstrates its ability to apply logical reasoning to determine the correct sequence of nodes to traverse from the start to the destination. This involves understanding the structure of the graph and making decisions based on the connections between nodes. Pattern Recognition: Phi-4-Reasoning can recognize patterns in the adjacency list and use them to find a solution. This is important for tasks that require identifying and following specific paths or routes. Versatility: The ability to solve a maze using an adjacency list showcases the model's versatility in handling different types of data structures and problem-solving scenarios. This is beneficial for AI developers who need to work with various data representations and algorithms. Efficiency: The model's ability to quickly and accurately find a valid path through the maze highlights its efficiency in solving complex problems. This is valuable for applications that require fast and reliable solutions. Conclusion: Phi-4-Reasoning's ability to solve a maze using an adjacency list demonstrates its advanced reasoning capabilities, making it a powerful tool for AI developers. Its proficiency in graph traversal, logical reasoning, pattern recognition, versatility, and efficiency makes it well-suited for tackling a wide range of complex problems. Deployment and Integration Phi-4-Reasoning can be deployed on various platforms, including Azure AI Foundry and Hugging Face. It supports quantization using tools like Microsoft Olive, making it suitable for deployment on edge devices such as IoT, laptops, and mobile devices. Phi-4-Reasoning is a groundbreaking AI model that offers advanced reasoning capabilities, high performance, and versatility. Its ability to handle complex reasoning tasks makes it an invaluable tool for AI developers, enabling them to create innovative solutions across various industries. References Make Phi-4-mini-reasoning more powerful with industry reasoning on edge devices | Microsoft Community Hub Phi-4 Reasoning Technical Paper Phi-4-Mini-Reasoning Technical Paper One year of Phi: Small language models making big leaps in AI | Microsoft Azure Blog PhiCookBook Access Phi-4-reasoning models Phi Models at Azure AI Foundry Models Phi Models on Hugging Face Phi Models on GitHub Marketplace ModelsBuilding AI Agents on edge devices using Ollama + Phi-4-mini Function Calling
The new Phi-4-mini and Phi-4-multimodal now support Function Calling. This feature enables the models to connect with external tools and APIs. By deploying Phi-4-mini and Phi-4-multimodal with Function Calling capabilities on edge devices, we can achieve local expansion of knowledge capabilities and enhance their task execution efficiency. This blog will focus on how to use Phi-4-mini's Function Calling capabilities to build efficient AI Agents on edge devices. What‘s Function Calling How it works First we need to learn how Function Calling works Tool Integration: Function Calling allows LLM/SLM to interact with external tools and APIs, such as weather APIs, databases, or other services. Function Definition: Defines a function (tool) that LLM/SLM can call, specifying its name, parameters, and expected output. LLM Detection: LLM/SLM analyzes the user's input and determines if a function call is required and which function to use. JSON Output: LLM/SLM outputs a JSON object containing the name of the function to call and the parameters required by the function. External Execution: The application executes the function call using the parameters provided by LLM/SLM. Response to LLM: Returns the output of Function Calling to LLM/SLM, and LLM/SLM can use this information to generate a response to the user. Application scenarios Data retrieval: convert natural language queries into API calls to fetch data (e.g., "show my recent orders" triggers a database query) Operation execution: convert user requests into specific function calls (e.g., "schedule a meeting" becomes a calendar API call) Computational tasks: handle mathematical or logical operations through dedicated functions (e.g., calculate compound interest or statistical analysis) Data processing: chain multiple function calls together (e.g., get data → parse → transform → store) UI/UX integration: trigger interface updates based on user interactions (e.g., update map markers or display charts) Phi-4-mini / Phi-4-multimodal's Function Calling Phi-4-mini / Phi-4-multimodal supports single and parallel Function Calling. Things to note when calling You need to define Tools in System to start single or parallel Function Calling If you want to start parallel Function Calling, you also need to add 'some tools' to the System prompt The following is an example Single Function Calling tools = [ { "name": "get_match_result", "description": "get match result", "parameters": { "match": { "description": "The name of the match", "type": "str", "default": "Arsenal vs ManCity" } } }, ] messages = [ { "role": "system", "content": "You are a helpful assistant", "tools": json.dumps(tools), # pass the tools into system message using tools argument }, { "role": "user", "content": "What is the result of Arsenal vs ManCity today?" } ] Full Sample : Click Parallel Function Calling AGENT_TOOLS = { "booking_fight": { "name": "booking_fight", "description": "booking fight", "parameters": { "departure": { "description": "The name of Departure airport code", "type": "str", }, "destination": { "description": "The name of Destination airport code", "type": "str", }, "outbound_date": { "description": "The date of outbound flight", "type": "str", }, "return_date": { "description": "The date of return flight", "type": "str", } } }, "booking_hotel": { "name": "booking_hotel", "description": "booking hotel", "parameters": { "query": { "description": "The name of the city", "type": "str", }, "check_in_date": { "description": "The date of check in", "type": "str", }, "check_out_date": { "description": "The date of check out", "type": "str", } } }, } SYSTEM_PROMPT = """ You are my travel agent with some tools available. """ messages = [ { "role": "system", "content": SYSTEM_PROMPT, "tools": json.dumps(AGENT_TOOLS), # pass the tools into system message using tools argument }, { "role": "user", "content": """I have a business trip from London to New York in March 21 2025 to March 27 2025, can you help me to book a hotel and flight tickets""" } ] Full sample : click Using Ollama and Phi-4-mini Function Calling to Create AI Agents on Edge Devices Ollama is a popular free tool for deploying LLM/SLM locally and can be used in combination with AI Toolkit for VS Code. In addition to being deployed on your PC/Laptop, it can also be deployed on IoT, mobile phones, containers, etc. To use Phi-4-mini on Ollama, you need to use Ollama 0.5.13+. Different quantitative versions are supported on Ollama, as shown in the figure below: Using Ollama, we can deploy Phi-4-mini on the edge, and implement AI Agent with Function Calling under limited computing power, so that Generative AI can be applied more effectively on the edge. Current Issues A sad experience - If you directly use the interface to try to call Ollama in the above way, you will find that Function Calling will not be triggered. There are discussions on Ollama's GitHub Issue. You can enter the Issue https://github.com/ollama/ollama/issues/9437. By modifying the Phi-4-mini Template on the ModelFile to implement a single Function Calling, but the call to Parallel Function Calling still failed. Resolution We have implemented a fix by making a adjustments to the template. We have improved it according to Phi-4-mini's Chat Template and re-modified the Modelfile. Of course, the quantitative model has a huge impact on the results. The adjustments are as follows: TEMPLATE """ {{- if .Messages }} {{- if or .System .Tools }}<|system|> {{ if .System }}{{ .System }} {{- end }} In addition to plain text responses, you can chose to call one or more of the provided functions. Use the following rule to decide when to call a function: * if the response can be generated from your internal knowledge (e.g., as in the case of queries like "What is the capital of Poland?"), do so * if you need external information that can be obtained by calling one or more of the provided functions, generate a function calls If you decide to call functions: * prefix function calls with functools marker (no closing marker required) * all function calls should be generated in a single JSON list formatted as functools[{"name": [function name], "arguments": [function arguments as JSON]}, ...] * follow the provided JSON schema. Do not hallucinate arguments or values. Do to blindly copy values from the provided samples * respect the argument type formatting. E.g., if the type if number and format is float, write value 7 as 7.0 * make sure you pick the right functions that match the user intent Available functions as JSON spec: {{- if .Tools }} {{ .Tools }} {{- end }}<|end|> {{- end }} {{- range .Messages }} {{- if ne .Role "system" }}<|{{ .Role }}|> {{- if and .Content (eq .Role "tools") }} {"result": {{ .Content }}} {{- else if .Content }} {{ .Content }} {{- else if .ToolCalls }} functools[ {{- range .ToolCalls }}{{ "{" }}"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}{{ "}" }} {{- end }}] {{- end }}<|end|> {{- end }} {{- end }}<|assistant|> {{ else }} {{- if .System }}<|system|> {{ .System }}<|end|>{{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}<|end|>{{ end }}<|assistant|> {{ end }}{{ .Response }}{{ if .Response }}<|user|>{{ end }} """ We have tested the solution using different quantitative models. In the laptop environment, we recommend that you use the following model to enable single/parallel Function Calling: phi4-mini:3.8b-fp16. Note: you need to bind the defined Modelfile and phi4-mini:3.8b-fp16 together to enable this to work. Please execute the following command in the command line: #If you haven't downloaded it yet, please execute this command firstr ollama run phi4-mini:3.8b-fp16 #Binding with the adjusted Modelfile ollama create phi4-mini:3.8b-fp16 -f {Your Modelfile Path} To test the single Function Calling and Parallel Function Calling of Phi-4-mini. Single Function Calling Parallel Function Calling Full Sample in notebook The above example is just a simple introduction. As we move forward with the development we hope to find simpler ways to apply it on the edge, use Function Calling to expand the scenarios of Phi-4-mini / Phi-4-multimodal, and also develop more usecases in vertical industries. Resources Phi-4 model on Hugging face https://huggingface.co/collections/microsoft/phi-4-677e9380e514feb5577a40e4 Phi-4-mini on Ollama https://ollama.com/library/phi4-mini Learn Function Calling https://huggingface.co/docs/hugs/en/guides/function-calling Phi Cookbook - Samples and Resources for Phi Models https://aka.ms/phicookbookUsing Advanced Reasoning Model on EdgeAI Part 1 - Quantization, Conversion, Performance
DeepSeek-R1 is very popular, and it can achieve the same capabilities as OpenAI o1 in advanced reasoning. Microsoft has also added DeepSeek-R1 models to Azure AI Foundry and GitHub Models. We can compare DeepSeek-R1 ith other available models through GitHub Models Playground Note This series revolves around deployment of SLMs to Edge Devices 'Edge AI' we will focus on the deployment advanced reasoning models, with different application scenarios. You can learn more in the following session AI Tour BRK453. In this experiement we want to deploy advanced reasoning models to the edge, so that they can run on edge devices with limited computing power and offline environments. At this time, the recommendation is to use the traditional ONNX model . We can use Microsoft Olive to convert the DeepSeek-R1 Distrill model. Getting started with Microsoft Olive is very straightforward. Install the Microsoft Olive library through the command line and Python 3.10+ (recommended) pip install olive-ai The DeepSeek-R1 Distrill model series has different parameters such as 1.5B, 7B, 8B, 14B, 32B, 70B, etc. This article is mainly based on the 1.5B, 7B, and 14B models (so a Small Language Model). CPU Inference Let's discuss 1.5B and 7B, which are models with lower parameter. We can directly use the CPU as computing for inference to test the effect (hardware environment Azure DevBox, AMD EPYC 7763 64-Core + 64GB Memory + 2T SSD) Quantization conversion olive auto-opt --model_name_or_path <Your DeepSeek-R1-Distill-Qwen-1.5B/7B local location> --output_path <Your Convert ONNX INT4 Model local location> --device cpu --provider CPUExecutionProvider --precision int4 --use_model_builder --log_level 1 You can download it directly from my Hugging face Repo (Note: This model is for testing and has not been fully tested by AI Content Safety or provided as an Offical Model) DeepSeek-R1-Distill-Qwen-1.5B-ONNX-INT4-CPU DeepSeek-R1-Distill-Qwen-7B-ONNX-INT4-CPU Running with ONNX Runtime GenAI Install ONNX Runtime GenAI and ONNX Runtime CPU support libraries pip install onnxruntime-genai pip install onnxruntime Sample Code https://github.com/kinfey/EdgeAIForAdvancedReasoning/blob/main/notebook/demo-1.5b.ipynb https://github.com/kinfey/EdgeAIForAdvancedReasoning/blob/main/notebook/demo-7b.ipynb Performance comparison 1.5B vs 7B We compare two different inference scenarios explain 1+1=2 1.5B quantized ONNX model memory occupied, time consumption and number of tokens generated: 7B quantized ONNX model memory occupied, time consumption and number of tokens generated 2. Find all pairwise different isomorphism groups with order 147 and no elements with order 49 1.5B quantized ONNX model memory occupied, time consumption and number of tokens generated: 7B quantized ONNX model memory occupied, time consumption and number of tokens generated Results of the numbers Through the test, we can see that the 1.5B model of DeepSeek is more suitable for use on CPU inference and can be deployed on traditional PCs or IoT devices. As for 7B, although it has better inference, it is not very effective on CPU operation. GPU Inference It is ideal if we have a GPU on the edge device. We can quantize and convert it to an ONNX model for CPU inference through Microsoft Olive. Of course, it can also be converted to a model for GPU inference. Here I take the 14B DeepSeek-R1-Distill-Qwen-14B as an example and make an inference comparison with Microsoft's Phi-4-14B Quantization conversion olive auto-opt --model_name_or_path <Your Phi-4-14B or DeepSeek-R1-Distill-Qwen-14B local path > --output_path <Your converted Phi-4-14B or DeepSeek-R1-Distill-Qwen-14B local path > --device gpu --provider CUDAExecutionProvider --precision int4 --use_model_builder --log_level 1 You can download it directly from my Hugging face Repo (Note: This model is for testing and has not been fully tested by AI Content Safety and not an Official Model) DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU Phi-4-14B-ONNX-INT4-GPU Running with ONNX Runtime GenAI CUDA Install ONNX Runtime GenAI and ONNX Runtime GPU support libraries pip install onnxruntime-genai-cuda pip install onnxruntime-gpu Compare the results in the GPU environment with Gradio It is recommended to use a GPU with more than 8G memory To increase the comparison of the results, we compare it with Phi-4-14B-ONNX-INT4-GPU and DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU to see the different results. We also show we use OpenAI o1-mini (it is recommended to use o1-mini through GitHub Models), Sample Code https://github.com/kinfey/EdgeAIForAdvancedReasoning/blob/main/notebook/Performance_AdvancedReasoning_ONNX_CPU.ipynb You can test any prompt on Gradio to compare the results of Phi-4-14B-ONNX-INT4-GPU, DeepSeek-R1-Distill-Qwen-14B-ONNX-INT4-GPU and OpenAI o1 mini. DeepSeek-R1 reduces the cost of inference models and produces more instructive results on professional problems, but Phi-4-14B also has advantages in reasoning and uses lower computing power to complete inference. As for OpenAI o1 mini, it is more comprehensive and can touch all problems. If you want to deploy to Edge Device, Phi-4-14B and quantized DeepSeek-R1 are good choices for you. This blog is just a simple test and the first in this series. Please share your feedback and continue the discussion in the Microsoft AI Discord Channel. Feel free to me a message or comment. We look forward to sharing more around the opportunity of EdgeAI and more content in this series. Resource DeepSeek-R1 in GitHub Models https://github.com/marketplace/models/azureml-deepseek/DeepSeek-R1 DeepSeek-R1 in Azure AI Foundry https://ai.azure.com/explore/models/DeepSeek-R1/version/1/registry/azureml-deepseek Phi-4-14B in Hugging face https://huggingface.co/microsoft/phi-4 Learn about Microsoft Olive https://github.com/microsoft/olive Learn about ONNX Runtime GenAI https://github.com/microsoft/onnxruntime-genai Microsoft AI Discord Channel BRK453 Exploring cutting-edge models: LLMs, SLMs, local development and more https://aka.ms/aitour/brk453
