Overview

OpenClaw on Intel iGPU via OpenVINO

Short summary: Run OpenClaw with a local Qwen3-8B LLM accelerated by Intel iGPU via OpenVINO GenAI in a Docker container for Windows with WSL2.

About Advantech Container Catalog (ACC)

Advantech Container Catalog is a comprehensive collection of ready-to-use, containerized software packages designed to accelerate the development and deployment of Edge AI applications. By offering pre-integrated solutions optimized for embedded hardware, it simplifies the challenges often faced with software and hardware compatibility, especially in GPU/NPU-accelerated environments.

Feature / Benefit	Description
Accelerated Edge AI Development	Ready-to-use containerized solutions for faster prototyping and deployment
Hardware Compatible	Reduces hardware and package incompatibility issues
GPU/NPU Access Ready	Supports passthrough for efficient hardware acceleration
Model Conversion & Optimization	Built-in model conversion and quantization recommendations
Optimized for CV & LLM Applications	Optimized stacks for vision and language workloads

Container Overview

This container packages OpenClaw with a local LLM inference stack that runs on Intel iGPU through OpenVINO GenAI. It is designed for Windows hosts using WSL2 and automates Docker, Node.js, OpenClaw, and model configuration to deliver a browser-based OpenClaw UI backed by Qwen3-8B-int4-ov.

Demo

Use Case

Local LLM service for edge AI applications on Intel iGPU
Offline inference and on-premises chatbot deployment
Proof-of-concept for OpenVINO-powered LLM acceleration in Windows/WSL2 environments

Key Features

Containerized OpenClaw with support for Intel iGPU acceleration via OpenVINO GenAI
Automatic Windows/WSL2 setup and Docker-based deployment
Local LLM inference using Qwen3-8B-int4-ov with ollama_openvino

Host Device Prerequisites

Item	Specification
Compatible Hardware	Intel Core Ultra CPU with Intel Graphics iGPU
Platform Version	Windows 10 IoT Enterprise LTSC 21H2 or Windows 11 (22H2+)
Host OS	Windows with WSL2 + Ubuntu 24.04
Required Packages	Docker Engine, Node.js 22, npm, OpenClaw, OpenVINO GenAI, ollama_openvino
Software Installation Guide	`README.md` in repository

Required Software Packages on Host Device

Component	Version	Description
Windows WSL2	Ubuntu 24.04	Linux environment for container runtime
Docker Engine	Latest supported	Container runtime without Docker Desktop
Node.js	22	Required by OpenClaw and setup scripts
OpenVINO GenAI	2026.1	Intel iGPU model inference backend
Intel GPU driver	32.0.101.8735+	Required for OpenVINO iGPU access

Container Environment Overview

Software Components in the Image

Component	Version	Description
OpenClaw	Latest stable	Web-based gateway for local LLM interaction
ollama_openvino	Built from source	OpenVINO provider for ollama-style model serving
OpenVINO GenAI	2026.1	Intel iGPU inference engine
Qwen3-8B-int4-ov	8B quantized model	Local LLM model running on Intel iGPU

Container Quick Start Guide

For container quick start and deployment details, see the step-by-step guide at: Advantech Containers Github

Supported AI Capabilities

Language Models

Model Family	Suggested Sizes	Memory Req.
Qwen3	8B int4	Medium

Optimization tips: Use the provided OpenVINO model build and Intel iGPU driver version 32.0.101.8735+ for best performance.

Supported AI Model Formats

Format	Support Level	Notes
OpenVINO	Full	Native Intel iGPU acceleration
ONNX	Partial	Possible via OpenVINO conversion workflows

Hardware Acceleration Support

Accelerator	Support Level	Compatible Libraries	Notes
Intel iGPU	Full	OpenVINO GenAI, ollama_openvino	Requires `/dev/dxg` passthrough from Windows WSL2

Troubleshooting & Notes

Common issues: Docker permission denied in WSL2, Intel iGPU not detected, WSL version too old, OpenClaw UI unreachable from Windows browser.
Known limitations: Requires WSL2 Ubuntu 24.04 and compatible Intel GPU driver; UI access may require Windows port proxy configuration on some systems.

Note: This page is based on the README.md for the OpenClaw OpenVINO Intel iGPU container.