# RF-DETR on edge devices

**URL:** <https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071>\
**Category:** 🤝  Community Help\
**Tags:** edge-device, raspberry-pi, rf-detr\
**Created:** [September 3, 2025, 5:27pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071 "2025-09-03T17:27:52Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![mila88](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mila88/32/8134_2.png) [@mila88](https://discuss.roboflow.com/u/mila88)\
**Post date:** [September 3, 2025, 5:27pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/1 "2025-09-03T17:27:53Z")

</div>

Hi! I was wondering if there is more information about RF-DETR deployment anywhere? I read this on the website: “RF-DETR is developed for projects that need a model that can run high speeds with a high degree of accuracy, and often on limited compute (like on the edge or low latency).” and found this when I googled it, however I cannot seem to find that information when I click on that page. Is it really possible that it could be deployed on a Raspberry Pi or is that google search result just misleading?

 ![Screenshot 2025-09-03 at 18.21.49](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/2X/a/aa16bb19d5edeea923a9932a8333715cee36510d.png)

---

<div class="post-metadata">

**Author:** ![Lake](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/lake/32/4110_2.png) [@Lake](https://discuss.roboflow.com/u/Lake)\
**Post date:** [September 3, 2025, 5:44pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/2 "2025-09-03T17:44:50Z")

</div>

Hi there, you can definitely deploy your RF-DETR model on a Raspberry Pi!

Here are a few links related to deployment in Roboflow:

- [Deploy a Model or Workflow | Roboflow Docs](https://docs.roboflow.com/deploy/deployment-overview)
- [Install on Raspberry Pi - Roboflow Inference](https://inference.roboflow.com/install/raspberry-pi/)

Raspberry Pi does have limitations with compute, but RF-DETR is designed with this in mind!

---

<div class="post-metadata">

**Author:** ![mila88](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mila88/32/8134_2.png) [@mila88](https://discuss.roboflow.com/u/mila88)\
**Post date:** [September 3, 2025, 6:22pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/3 "2025-09-03T18:22:43Z")

</div>

Hi, thank you so much for the quick reply! Do you happen to know where I can find that reference about RF-DETR’s capability to be deployed on a Raspberry Pi, so that I can cite it? Many thanks!

---

<div class="post-metadata">

**Author:** ![Lake](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/lake/32/4110_2.png) [@Lake](https://discuss.roboflow.com/u/Lake)\
**Post date:** [September 3, 2025, 6:30pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/4 "2025-09-03T18:30:59Z")

</div>

The best I can supply is this section: [Install on Raspberry Pi - Roboflow Inference](https://inference.roboflow.com/install/raspberry-pi/#hardware-acceleration)

The only models _not_ supported are models that require a large GPU, such as Florence 2.

---

<div class="post-metadata">

**Author:** ![mila88](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mila88/32/8134_2.png) [@mila88](https://discuss.roboflow.com/u/mila88)\
**Post date:** [September 3, 2025, 6:54pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/5 "2025-09-03T18:54:06Z")

</div>

Thank you! Would that be for all of the models or perhaps Nano or Small?

I just noticed this on the repo, but I‘ve started training my models before this update:

`2025/07/23`: Released three new checkpoints for RF-DETR: Nano, Small, and Medium.

Thanks a lot once again!

---

<div class="post-metadata">

**Author:** ![Lake](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/lake/32/4110_2.png) [@Lake](https://discuss.roboflow.com/u/Lake)\
**Post date:** [September 3, 2025, 7:09pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/6 "2025-09-03T19:09:39Z")

</div>

All sizes should be able to run on the Pi! You will get faster performance from the smaller model!

---

<div class="post-metadata">

**Author:** ![mila88](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mila88/32/8134_2.png) [@mila88](https://discuss.roboflow.com/u/mila88)\
**Post date:** [September 3, 2025, 7:30pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/7 "2025-09-03T19:30:14Z")

</div>

Okay amazing, I have been using it for early wildfire smoke detection research and this is very reassuring! 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:** [September 10, 2025, 7:31pm UTC](https://discuss.roboflow.com/t/rf-detr-on-edge-devices/11071/8 "2025-09-10T19:31:06Z")

</div>

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.
