Text of developer.amd.com › playbooks as Styx crawled it on Nov 19, 2026. The page may have changed since. Only its words are kept, without pictures or layout, and only the first part of a long page.

Open the live page

AMD AI Playbooks

Skip to content Start Building with AMD AI Playbooks Step-by-step guides to run AI workloads on AMD hardware. From inference to fine-tuning, get up and running fast. The one-stop solution for local AI development and inference. User Guide AMD Sync AMD Ryzen™ AI processors for next generation AI PC experiences. AMD Radeon™ AI PRO Graphics for local AI inference and development. Device Platform System memory Difficulty Filter No playbooks available for this combination yet.

Try selecting a different device family, device, OS, difficulty, or system memory. What's New Coming Soon New Featured Pre-Installed Advanced Clustering Four Ryzen™ AI Halos with RCCL Set up a multi-node cluster using four Ryzen™ AI Halo devices with RCCL for distributed workloads 90 min clustering distributed +3 more Coming Soon New Featured Pre-Installed Advanced Clustering Four Ryzen™ AI Halos with RPC Set up distributed inference using RPC server across four Ryzen™ AI Halo devices with llama.cpp to run 1T+ models 120 min clustering rpc +4 more Coming Soon New Featured Pre-Installed Beginner Getting Started with Your Ryzen AI Halo (Project Zenith) Tour the preinstalled AI stack and developer tooling on your Windows Ryzen AI Halo, then connect the Zenith agent tools to a local model served by Lemonade.

30 min lemonade getting-started +5 more All Playbooks Coming Soon New Featured Pre-Installed Intermediate Automating Workflows with n8n and Local LLMs Build an AI-powered news summarizer using n8n and Lemonade. 45 min automation n8n +3 more Coming Soon New Featured Pre-Installed Beginner Generating Images with ComfyUI and Z Image Turbo Create stunning AI-generated images using ComfyUI with Z Image Turbo. 15 min image-generation comfyui +1 more Coming Soon New Featured Pre-Installed Beginner Local LLM Coding with VSCode and Qwen3-Coder Use VS Code with locally-running Qwen3-Coder for private code assistance.

30 min coding vscode +2 more Coming Soon New Featured Pre-Installed Beginner Running and Serving LLMs with LM Studio Set up LM Studio and LM Studio Server to run and serve large language models locally. 30 min lm-studio rocm +3 more Coming Soon New Featured Pre-Installed Beginner Running LLMs on PyTorch with AMD ROCm™ Software Learn to run powerful language models on your PC with PyTorch and AMD ROCm™ software to summarize documents quickly and easily.

30 min pytorch rocm +3 more Coming Soon New Featured Pre-Installed Advanced Build a GitHub-to-Slack Development Digest with Agent Canvas Configure Agent Canvas, GitHub MCP, Slack MCP, and a scheduled OpenHands automation that posts a local-LLM digest. 60 min openhands agent-canvas +5 more Coming Soon New Featured Pre-Installed Advanced Building Custom GPU Kernels with PyTorch and AMD ROCm™ Write and optimize custom GPU kernels using PyTorch and AMD ROCm™ software 60 min pytorch rocm +3 more Coming Soon New Featured Pre-Installed Beginner Building Your First Agent with GAIA Build a 100% local AI agent — no cloud APIs needed.

Use the GAIA SDK to create a hardware advisor. 15 min gaia agent-sdk +3 more Coming Soon New Featured Pre-Installed Beginner Chatting with LLMs in Open WebUI Use Open WebUI to chat with LLMs locally. 30 min openwebui chat +4 more Coming Soon New Featured Pre-Installed Advanced Clustering Two Ryzen™ AI Halos with RCCL Set up a multi-node cluster using two Ryzen™ AI Halo devices with RCCL for distributed workloads 90 min clustering distributed +3 more Coming Soon New Featured Pre-Installed Advanced Clustering Two Ryzen™ AI Halos with RPC Set up distributed inference using RPC server across two Ryzen™ AI Halo devices with llama.cpp to run 350B+ models 90 min clustering rpc +4 more Coming Soon New Featured Pre-Installed Intermediate Fine-Tuning LLMs with LLaMA Factory Fine-tune large language models (LLMs) using LLaMA Factory and LoRA techniques.

60 min Llama Factory lora +1 more Coming Soon New Featured Pre-Installed Intermediate Fine-Tuning LLMs with PyTorch and AMD ROCm™ Software Fine-tune large language models (LLMs) using PyTorch and ROCm. 45 min pytorch fine-tuning +2 more Coming Soon New Featured Pre-Installed Intermediate Fine-Tuning LLMs with Unsloth Use Unsloth for memory-efficient fine-tuned LLMs™ 45 min unsloth sft +2 more Coming Soon New Featured Pre-Installed Beginner Getting Started with Lemonade Learn to run Gen AI models locally with Lemonade, an open-source local AI server.

30 min lemonade cpu +3 more Coming Soon New Featured Pre-Installed Beginner Getting Started with Ollama Install Ollama and run LLMs locally — chat from the terminal, desktop app, or REST API. 15 min ollama llm +3 more Coming Soon New Featured Pre-Installed Beginner Getting Started with OpenHands and a Local LLM Install Agent Canvas, connect a local Lemonade model, and run your first OpenHands coding agent on your AMD Ryzen™ AI.

20 min openhands agent-canvas +3 more Coming Soon New Featured Pre-Installed Beginner Getting Started with vLLM Learn how to run inference and serving using containerized vLLM on the integrated GPU 30 min vllm inference +2 more Coming Soon New Featured Pre-Installed Intermediate Local Computer Vision with AMD Ryzen™ AI NPU Build local perception capabilities using the CVML SDK on top of Ryzen AI and AMD ROCm™ software 45 min cvml perception +4 more Coming Soon New Featured Pre-Installed Intermediate Real-Time Speech-to-Speech Translation Build a real-time speech-to-speech translation on your local hardware.

30 min speech translation +2 more Coming Soon New Featured Pre-Installed Beginner Remote Development with AMD Sync Install AMD Sync on your laptop and get one-click remote VS Code, Terminal, JupyterLab, and Live Metrics on your AMD Ryzen™ AI Halo. 15 min amd-sync ssh +4 more Coming Soon New Featured Pre-Installed Advanced Running DeepSeek V4 Flash with ds4 Deploy DeepSeek V4 Flash locally using the ds4 inference engine and manage models interactively with ds4-cockpit.

45 min deepseek ds4 +3 more Coming Soon New Featured Pre-Installed Intermediate Running Hermes Agent Locally with Lemonade Server Install and configure Hermes Agent autonomous AI agent with Lemonade Server as its local AI backend. 45 min hermes lemonade +4 more Coming Soon New Featured Pre-Installed Intermediate Running OpenClaw Locally with Lemonade Server Install and configure OpenClaw autonomous AI agent with Lemonade Server.

45 min openclaw lemonade +3 more more coming soon Frequently Asked Questions What are AMD AI Playbooks? Playbooks are step-by-step guides for building and running AI workloads on AMD hardware, including AMD Ryzen™ AI APUs and Radeon™ GPUs. They are published in a public GitHub repository and provide hands-on, reproducible workflows from environment setup to running models locally and building real applications. Is access to Playbooks free?

Yes. Playbooks are publicly available on the GitHub Playbooks repo and free to use. You can clone, run, and modify them to fit your own development workflows. What hardware and operating systems are supported? Playbooks support: Hardware: Ryzen™ AI Halo, Ryzen™ AI APUs, and Radeon™ GPUs Operating Systems: Windows and Linux Use the platform filters to view playbooks compatible with your system configuration. Supported processors by device family are listed below.

Device Family Processor Ryzen™ AI Halo Ryzen™ AI Max+ Ryzen™ AI APUs Ryzen™ AI Max+, Ryzen™ AI 300 HX, & Ryzen™ AI 300 Radeon™ GPUs RX 7900 Series & RX 9000 Series Do I need cloud access to Playbooks? No. Playbooks are designed to run locally on your machine. This allows you to develop, test, and iterate directly on your hardware. Some workflows may optionally integrate with cloud services, but local execution is the default.

What's included in a Playbook? Each playbook typically includes: Environment setup instructions (drivers, dependencies) Scripts or commands to run models Configuration files and parameters Optional application layers such as APIs

The rest of this page is on the live site.