Updated 09/08/2026
AI Playground, an easy-to-use Generative AI app suite for Intel AI PCs, powered by Intel® Core™ Ultra Processors, Intel Core Series 3, Intel® Arc™ discrete GPUs, or Nvidia RTX GeForce GPUs. AI Playground is available as an open-source project with packaged Windows or Linux desktop installers. AI Playground supports OpenVINO, Llama.cpp Vulkan, PyTorch for local models support, along with frontier cloud model support via API, with access to Claude, ChatGPT, Gemini, and Grok models. Local model support allows you to point and click your way to use 100s of popular open weight models like Qwen 3.8, Gemma 4, or GPT-OSS for chat, or visual generation models like Flux.2 Klein, Z-Image Turbo, SDXL, LTX Video, WAN 2.2 and ComfyUI workflows.
NEW: AI Playground now supports both Windows and Linux, including features such as Game Agent for AI generated video games, Audio Gen for text to speech generation, and Home Agent, which can access and run AI Playground remotely using your smart phone. AI Playground is also available for Intel Core Series 3 systems, learn more.
Download AI Playground:
Be sure to update your Graphics and NPU drivers(for supported Intel Core Ultra devices). Also note while an installer makes the process easy to get up and running, this is open source beta software, where components and version can have conflicts. Check the Troubleshooting section of the project readme for known issues.
Back-up any valued content generated from a previous installation before installing
| AI Playground Files as of Sept 08, 2026 |
Version | Links |
|
AI Playground 3 |
Latest |
Release Notes | Windows Download | Linux Download | Manual |
|
Source Code and Repo |
Latest |
|
|
Community/Support |
|
Join Intel Insiders Discord, and access our dedicated |
What is AI Playground
See latest feature update here: AI Playground beta is a free to download and app for doing Gen AI inferencing on your Intel Core Ultra or Intel Arc GPU based systems. AI Playground curates over 60 top open-source models and ties them to a variety of point and click features for chat, image generation, image generation and video.
Easy To Use: AI Playground is designed to be easy to use, allowing you to get working with AI quickly. AI Playground will prompt you if and when a model is needed for a task, allowing you to download one, or provide your own. And our settings are written and designed using terms that make sense for the task without you having to be educated on AI just to use AI.
All-In-One AI Hub: Switch seamlessly between usages of image creation, image editing, and a chat LLM . AI Playground keeps it all together in one easy-to-use experience. Currently AI Playground supports Stable Diffusion 1.5, Stable Diffusion XL, Flux.1-Schnell, LCM Fast LoRAs, Image Upscale, Image to Image Stylization, Inpainting, Outpainting, ChatBot with session history context and LLM RAG features allowing you to get summaries, and search content from your local computer.
Flexible: AI Playground will provide access to models for all features, and more advanced users can install their favorite models and tweak manual settings, to configure AI Playground to work the way they want it to work.
Local or Hybrid: AI Playground features can all be run locally, therefore your prompts, and the output never leave your computer. This provides you privacy and control of your content and input for working with AI, and puts you in control without an upstream entity over your shoulder censoring your prompts or capturing your data and content. Alternatively, choose to use frontier models from the cloud when you need a more powerful capable model.
Hardware Optimized: AI Playground takes advantage of Intel Arc GPU architecture leveraging our powerful Intel Xe Cores and XMX engine.
Open: AI Playground is also an open-source project where our community can clone, fork or help us address features and capabilities of the main repo.
Core Features
AI Playground is a locally run Generative AI application suite that acts as an offline alternative to cloud tools such Gemini ChatGPT and Grok. AI Playground is intended to give consumers and AI curious prosumer easy and intuitive access to a wide variety of generative AI features using their Intel powered AI PC. This means you can be offline, without loading sensitive or personal data to 3rd party sites, for free, in a single app without having to know how to install and manage multiple AI backend frameworks.
Key features:
Latest Chat Models: Support for Qwen, Gemma, DeepSeek and GPT-OSS models: AI playground makes a variety of chat models available some with specific features like vision, reasoning, or tool calling. Download and favorite models we provide, or add your own models for use in AI Playground.
Hybrid Cloud: Choose to use Grok, Gemini, ChatGPT or Claude models when you need a more powerful model
Agentic Presets: Game Agent, Quick Coder and Home Agent allow you to leverage agents for specific use cases like creating video games, or tasking your AI Playground PC to do tasks while away using a smart phone chat application:
Audio Gen: Generate voice files or convert voice to written text with these audio generation tools
Image and Image Edit Generation: Rich image generation and editing are some of AI Playgrounds most powerful and popular features. From SDXL to Flux.2 Klein, or Z-image models and features like image upscale, edit-by-prompt, and image-to-3D give you power and control to take basic graphic ideas to the next level.
Video: Generate amazing video clips from text or images using LTX or WAN video models – Best on workstations and desktops with discrete GPUs
Multi-Modal and Remote Access
Voice Mode and Speech Gen: AI Playground now supports a voice mode. From the app settings you can turn on Voice mode. This will load an AI voice model to the NPU of your Intel Core Ultra PC. When enabled a microphone icon will be available in the prompt. Simple click the icon and voice your prompt. Voice mode will convert your voice to text prompt. Additionally you can use the Audio Gen mode to generate audio speech files.
Vision Model Support: AI Playground chat supports Vision Model support. With Vision support you can paste or load an image to Chat mode and have AI Playground analyze the image, giving you insight, answers and information about the image
Home Agent: Home Agent is a special feature in AI Playground that allows you to run any AI Playground features while away from your AI PC, using a chat tool from a smart phone such as Telegram or Slack: See Home Agent in action
Agentic Tools. AI Playground exposes smart presets like Game Agent and Quick Coder to assist in complex tasks, plus tool calling and MCP support allow you to use a core model to do tasks across AI Playground features while controlling other applications like Blender. within a single chat discussion.
Unified Prompt:
AI Playground now deploys a single unified prompt window for all AI Playground features. This design aligns AI Playground to familiar AI tools like Gemini, Chat GPT and Grok. You can now choose to experience AI Playground in a light-colored theme
Backends:
- OpenVINO: OpenVINO provides the best performance when using OpenVINO IR Models with the ability to target CPU, NPU or GPU. AI Playground provides access to a variety of chat, reasoning, vision and tool calling models in OpenVINO format in Chat mode:
- Llama.CPP: For access to latest models in GGUF format, AI Playground provides models such as Qwen 3VL, DeepSeek R1 Distilled, and GPT-OSS 20B in GGUF format, for use in the chat mode
- PyTorch: PyTorch is primarily used to support image diffusion based models for image generation, image editing and video generation. We provide access to models such as SDXL, Flux.1 Schnell, Z-Image-Turbo and more
- ComfyUI: is a backend solution allowing us to easily create and deploy custom workflows for specific image and video Preset
ComfyUI Editor
For users interested in diving into ComfyUI workflows, or those already familiar with ComfyUI, we’ve provided direct access to its workflow editor, allowing users to edit or create workflows for use either directly from ComfyUI or in AI Playground. We encourage and welcome the community created workflows submitted and shared to AI Playground via Pull Requests to our project
See AI Playground In Action
AI Playground 3.0 at CES 2026
Demo Reel
Introduction Video of Core Features
Install Image Checkpoints
For more information, visit the AI Playground project on GitHub, or join our Intel Insiders Discord to engage directly with Intel and our Community on AI Playground
Notices and Disclaimers: For information on AI Playground terms, license and disclaimers, visit the project and files on GitHub repo: