Try the Model

Use the widget below to experiment with Qwen2.5-VL. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

Qwen2.5-VL is a multimodal vision-language model developed by the Qwen team at Alibaba Cloud. You can use Qwen2.5-VL for a wide variety of tasks, including visual question answering, document OCR, and object detection. The model is available in three sizes: 3B, 7B, and 72B.

Across benchmarks, the largest Qwen2.5-VL model performs competitively when evaluated against other state-of-the-art models like GPT-4o and Gemini-2 Flash. For example, on the DocVQA, InfoVQA, and CC-OCR benchmarks, Qwen2.5-VL outperforms GPT-4o.

In the Qwen2.5 GitHub repository, the project authors note the following as key tasks on which the model performs better than previous Qwen models:

Document understanding
Video understanding
Object identification and grounding
Object counting
Agentic capabilities for computer screen inputs

Qwen2.5-VL License

Qwen2.5-VL

is licensed under a

Apache 2.0

license.

Performance

Deploy a Qwen2.5-VL API

You can use Roboflow Inference to deploy a

Qwen2.5-VL

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with Qwen2.5-VL

You can automatically label a dataset using Qwen2.5-VL with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use Qwen2.5-VL to train a computer vision model.

No items found.