<!-- # hard line break macro for HTML -->

<a id="model-zoo-qwen3-vl-4b-instruct-torch"></a>

# qwen3-vl-4b-instruct-torch

Balanced vision-language model for object detection via 2D grounding.

**Details**

- Model name: `qwen3-vl-4b-instruct-torch`
- Model source: [https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct)
- Model author: Qwen Team, Alibaba
- Model license: Apache 2.0
- Model size: 8.38 GB
- Exposes embeddings? no
- Tags: `detection, vlm, torch, transformer, zero-shot`

**Requirements**

- Packages: `torch, torchvision, transformers>=4.51.0, accelerate, qwen-vl-utils`
- CPU support
  - yes
- GPU support
  - yes

**Example usage**

```python
import fiftyone as fo
import fiftyone.zoo as foz

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("qwen3-vl-4b-instruct-torch")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)
```