# Using yolo12n in r3forth

**URL:** <https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476>\
**Category:** Community Showcase\
**Created:** [September 21, 2025, 8:16pm UTC](https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476 "2025-09-21T20:16:45Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![PHReda](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/phreda/32/912_2.png) [@PHReda](https://community.ultralytics.com/u/PHReda)\
**Post date:** [September 21, 2025, 8:16pm UTC](https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476/1 "2025-09-21T20:16:45Z")

</div>

I successfully ran the YOLO12N and YOLO11Npose models on CPU using the ONNXRuntime library, implemented in R3Forth programming language.

videos:

[![](https://us1.discourse-cdn.com/flex001/uploads/ultralytics1/original/1X/15934b176c4fc6d9cd86351dffefad53c2313f5a.jpeg "r3 + SDL2 + onnxruntime + yolo12n + ffmpeg ..") ](https://www.youtube.com/watch?v=G6C6qaxqTGI)

---

<div class="post-metadata">

**Author:** ![PHReda](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/phreda/32/912_2.png) [@PHReda](https://community.ultralytics.com/u/PHReda)\
**Post date:** [September 21, 2025, 8:17pm UTC](https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476/2 "2025-09-21T20:17:30Z")

</div>

another video:

[![](https://us1.discourse-cdn.com/flex001/uploads/ultralytics1/original/1X/ffb280530a873342b3eb2a23df97061e1811795a.jpeg "Performing AI inference with R3Forth. Try it out!") ](https://www.youtube.com/watch?v=83Ws3uFB3Cw)

---

<div class="post-metadata">

**Author:** ![pderrenger](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/pderrenger/32/73_2.png) [@pderrenger](https://community.ultralytics.com/u/pderrenger)\
**Post date:** [September 22, 2025, 1:28pm UTC](https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476/3 "2025-09-22T13:28:49Z")

</div>

Awesome demos—ONNX Runtime + R3Forth is a cool combo! For stability and CPU speed, I’d recommend using YOLO11 over YOLO12; you can export YOLO11n and YOLO11n‑pose to ONNX directly:

```bash
yolo export model=yolo11n.pt format=onnx dynamic=True
yolo export model=yolo11n-pose.pt format=onnx dynamic=True

```

If you prefer Python, `simplify=True` can help with interoperability:

```python
from ultralytics import YOLO
YOLO('yolo11n.pt').export(format='onnx', dynamic=True, simplify=True)

```

If others want to reproduce this, the steps in our [ONNX export guide for YOLO11](https://docs.ultralytics.com/integrations/onnx/) cover CLI/Python usage and ONNX Runtime tips. If you can share your R3Forth bindings or a gist, we’d love to point the community to it.

---

<div class="post-metadata">

**Author:** ![PHReda](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/phreda/32/912_2.png) [@PHReda](https://community.ultralytics.com/u/PHReda)\
**Post date:** [September 22, 2025, 2:01pm UTC](https://community.ultralytics.com/t/using-yolo12n-in-r3forth/1476/4 "2025-09-22T14:01:02Z")

</div>

Thank you for the feedback. I thought YOLO12 would be more advanced or faster, but I’ll test it myself to see if there’s any difference compared to YOLO11.  
The camera example can be tested by downloading the language distribution from:

> **[GitHub - phreda4/r3: r3 programing language - ColorForth inspired](https://github.com/phreda4/r3)**
>
> r3 programing language - ColorForth inspired

I haven’t included the ONNX files due to their size, but you can download them from here:

> **[Release files for ia demos · phreda4/r3](https://github.com/phreda4/r3/releases/tag/onnx)**
>
> unzip in onnx/ folder in root
> used by code in r3/onnx

The encoding of the input and output tensors is done without using external libraries, so figuring out the details of how the data is processed took quite a bit of time, but I believe it results in faster execution.