# How to Install and Use a Custom Model (.pt or ONNX) from Roboflow

**URL:** <https://discuss.roboflow.com/t/how-to-install-and-use-a-custom-model-pt-or-onnx-from-roboflow/6391>\
**Category:** 🤝  Community Help\
**Tags:** convert, export\
**Created:** [July 2, 2024, 5:00pm UTC](https://discuss.roboflow.com/t/how-to-install-and-use-a-custom-model-pt-or-onnx-from-roboflow/6391 "2024-07-02T17:00:31Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mustafa\_Gülsoy](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mustafa_g%C3%BClsoy/32/4999_2.png) [@Mustafa\_Gülsoy](https://discuss.roboflow.com/u/Mustafa_G%C3%BClsoy)\
**Post date:** [July 2, 2024, 5:00pm UTC](https://discuss.roboflow.com/t/how-to-install-and-use-a-custom-model-pt-or-onnx-from-roboflow/6391/1 "2024-07-02T17:00:32Z")

</div>

I have trained a custom machine learning model and exported it in .pt and ONNX formats using Roboflow. I would like to know the steps required to install and use these models in my own projects. Could someone provide a detailed guide or point me to the necessary resources for:

1. Installing the model on my local machine.
2. Integrating the model into a Python project.
3. Running inference with the model on new data.

Any help with example code or best practices would be greatly appreciated! Thank you.

---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/1X/bb6edbfa56d0cf2ee603f061e9e09103502cc8cc.png) [@system](https://discuss.roboflow.com/u/system)\
**Post date:** [July 23, 2024, 5:00pm UTC](https://discuss.roboflow.com/t/how-to-install-and-use-a-custom-model-pt-or-onnx-from-roboflow/6391/2 "2024-07-23T17:00:44Z")

</div>

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.