# openbmb/MiniCPM-V-4_5
#### NOTE
This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the
[minicpm-v](../../plugins/plugins_ecosystem/minicpm_v.html) plugin, maintained by the community.
It is not part of FiftyOne core and may have special installation requirements.
Please review the plugin documentation and license before use.
MiniCPM-V 4.5 is the latest and most capable model in the MiniCPM-V series. The model is built on Qwen3-8B and SigLIP2-400M with a total of 8B parameters..
**Details**
- Model name: `openbmb/MiniCPM-V-4_5`
- Model source: [https://huggingface.co/openbmb/MiniCPM-V-4_5](https://huggingface.co/openbmb/MiniCPM-V-4_5)
- Model author: Open Lab for Big Model Base
- Model license: MiniCPM Model License
- Exposes embeddings? no
- Tags: `detection, keypoints, ocr, VLM, classification, zero-shot`
**Requirements**
- Packages: `huggingface-hub, transformers, torch, torchvision`
- CPU support
- yes
- GPU support
- yes
**Example usage**
```python
import fiftyone as fo
import fiftyone.zoo as foz
foz.register_zoo_model_source("https://github.com/harpreetsahota204/minicpm-v")
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("openbmb/MiniCPM-V-4_5")
dataset.apply_model(model, label_field="predictions")
session = fo.launch_app(dataset)
```