VLM Edge Studio

[#1]

Sure — here’s a short NXP Community post draft for VLM Edge Studio:

---

Running Vision-Language Models on i.MX with Ara240 DNPU using VLM Edge Studio

In this post, I want to share a quick walkthrough of VLM Edge Studio, an NXP launcher application designed to interact with supported Vision-Language Models running locally on FRDM i.MX platforms with Ara240 DNPU acceleration. [github.com]

VLM Edge Studio provides a Qt/QML-based GUI for model selection, prompt input, and visual interaction with locally running VLMs at the edge. It communicates with the Ara240 Runtime SDK through the eIQ AAF Connector using a REST-based interface and streaming token responses. [github.com]

Supported Platforms

• FRDM i.MX 8M Plus [github.com]
• FRDM i.MX 95 [github.com]

Key Features

• Local Vision-Language Model inference on supported i.MX platforms [github.com]
• Ara240 DNPU acceleration [github.com]
• GUI-based model selection and prompt input [github.com]
• Streaming token output [github.com]
• Integration with eIQ AAF Connector and Ara240 Runtime SDK [github.com]
• Support for camera-based visual input using a USB-C HD camera [github.com]

Supported Model

The current version supports:

• Qwen2.5-VL-7B-Instruct-Ara240 [github.com]

This model is provided as an Ara240-compatible model.dvm file and is intended for local execution on the target platform. [github.com]

Basic Installation

After making sure the Ara240 Runtime SDK is installed on the target board, copy the Debian package to the board:

scp vlm-edge-studio.deb root@<ip_addr>:

Install it with:

dpkg -i vlm-edge-studio.deb

The installation may take a few minutes because the model needs to be extracted during setup. [github.com]

Running VLM Edge Studio

Start the application with:

run_vlm_edge_studio

Before launching, make sure the Ara240 runtime service is running:

systemctl status rt-sdk-ara2.service --no-pager -l

Once the GUI appears, click LOAD to load the model. After the model is ready, enter a prompt and submit it to interact with the VLM locally on the i.MX platform. [github.com]

Walkthrough Video

In the attached video, I show how to launch VLM Edge Studio, load the supported Vision-Language Model, submit a prompt, and interact with the model running locally with Ara240 DNPU acceleration.

Video:

Notes and Limitations

• A single application instance can load only one model at a time. [github.com]
• Multiple models cannot currently be assigned to different endpoints within the same instance. [github.com]
• The UI is designed for 1920x1080 resolution; higher-resolution displays may show layout issues. [github.com]
• A proper 5V/3A power supply is recommended to avoid instability or board resets during inference. [github.com]

Summary

VLM Edge Studio is a useful tool for evaluating local Vision-Language Model inference on NXP i.MX platforms using Ara240 DNPU acceleration. It provides a simple workflow for loading the model, entering prompts, and interacting with visual-language AI directly at the edge. [github.com]

Link

VLM Edge Studio repository:
https://github.com/nxp-imx-support/vlm-edge-studio