# New Release: Ultralytics v8.4.80

**URL:** https://community.ultralytics.com/t/new-release-ultralytics-v8-4-80/2085
**Category:** Discussion
**Tags:** announcements, ultralytics-official, releases
**Created:** [June 27, 2026, 1:33pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-80/2085 "2026-06-27T13:33:37Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)
#### Post date: [June 27, 2026, 1:33pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-80/2085/1 "2026-06-27T13:33:37Z")

</div>

## Ultralytics v8.4.80 is here 🚀

**Quick summary:** Ultralytics v8.4.80 is a deployment-focused release that makes model export precision much simpler with a new unified `quantize` argument, while also improving multi-GPU validation, OBB training stability, network reliability, and documentation across the Ultralytics ecosystem.

If you export models regularly, validate across multiple GPUs, or train OBB models, this release should make your workflow smoother and more robust. You can explore the release on [GitHub Releases](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.80).

* * *

## 🌟 Highlights

### New unified `quantize` export argument

The biggest change in v8.4.80 is the new `quantize` export argument, introduced in [PR #24918](https://github.com/ultralytics/ultralytics/pull/24918) by [@onuralpszr](https://github.com/onuralpszr).

This replaces the older `half=True` and `int8=True` export switches with a cleaner, more flexible interface:

- `quantize=32` for FP32
- `quantize=16` for FP16
- `quantize=8` for INT8
- Advanced modes like `quantize="w8a16"` where supported

This update makes export settings easier to read, easier to automate, and better aligned with modern hardware-specific quantization workflows. Existing `half` and `int8` arguments remain supported for now, so current scripts should continue working during migration. ✅

Example:

```python
from ultralytics import YOLO

model = YOLO("yolo26n.pt")
model.export(format="onnx", quantize=16)

```

### Export docs and integrations updated

To support the new `quantize` workflow, export examples and docs were refreshed across many backends and deployment targets, helping keep Ultralytics YOLO export guidance consistent and future-ready. 📦

* * *

## Improvements

### Better distributed validation results across GPUs

In multi-GPU validation, confusion matrices are now gathered across all DDP workers instead of reflecting only a single process. This improvement landed in [PR #24803](https://github.com/ultralytics/ultralytics/pull/24803) by [@Y-T-G](https://github.com/Y-T-G), and should produce more accurate confusion matrix plots for distributed evaluation. 📈

### More stable OBB training

A fix in [PR #24933](https://github.com/ultralytics/ultralytics/pull/24933) by [@Y-T-G](https://github.com/Y-T-G) improves training stability for oriented bounding box models by preventing very small sub-stride boxes from triggering invalid loss behavior or NaNs. This is especially helpful for small-object OBB workloads. 🎯

### Improved request timeout and retry behavior

Network-related reliability was strengthened with:

- [PR #24743](https://github.com/ultralytics/ultralytics/pull/24743) by [@raimbekovm](https://github.com/raimbekovm), which forwards socket timeout in smart requests
- [PR #24734](https://github.com/ultralytics/ultralytics/pull/24734) by [@raimbekovm](https://github.com/raimbekovm), which adds request timeouts in Platform-related calls and downloads

These changes should reduce cases where requests stall indefinitely and improve failure handling. 🌐

### MLflow integration tests restored

[PR #24728](https://github.com/ultralytics/ultralytics/pull/24728) by [@raimbekovm](https://github.com/raimbekovm) restores and modernizes MLflow integration tests for newer MLflow versions, improving confidence in experiment logging support. 🧪

* * *

## 📚 Documentation updates

Several docs were improved in this release:

- Tracking persistence and tracker selection were clarified in [PR #24889](https://github.com/ultralytics/ultralytics/pull/24889) by [@joeydufourd](https://github.com/joeydufourd), including better guidance around `persist=True`, `botsort.yaml`, and `bytetrack.yaml`
- The isolating segmentation guide was fixed in [PR #24701](https://github.com/ultralytics/ultralytics/pull/24701) by [@raimbekovm](https://github.com/raimbekovm)
- Ultralytics Platform dataset upload docs now better explain browser video codec support in [PR #24802](https://github.com/ultralytics/ultralytics/pull/24802) by [@laodouya](https://github.com/laodouya), including clearer upload expectations for browser-based video handling 🎥

For users building end-to-end workflows, the [Ultralytics Platform documentation](https://docs.ultralytics.com/platform) remains the best place to learn more about annotating datasets, training, deploying, and monitoring models.

* * *

## 🙌 New contributor

A big welcome to [@joeydufourd](https://github.com/joeydufourd), who made their first contribution with [PR #24889](https://github.com/ultralytics/ultralytics/pull/24889). Thank you for helping improve the docs and user experience! 🎉

* * *

## Why this release matters

v8.4.80 may not be a major model-launch release, but it delivers meaningful quality-of-life improvements for production and research workflows:

- Simpler export precision settings with `quantize`
- Better support for future mixed-precision deployment
- More accurate validation outputs in distributed setups
- More stable OBB training
- Fewer frustrating request hangs
- Clearer docs for tracking, segmentation, and Platform uploads

For new projects, we recommend using [Ultralytics YOLO26](https://platform.ultralytics.com/ultralytics/yolo26), our latest stable model family, which is smaller, faster, more accurate than YOLO11, and natively end-to-end.

* * *

## Try it out

Update with:

```bash
pip install -U ultralytics

```

Then give the new export flow a spin with your favorite model, and let us know how it works for you. Feedback, bug reports, and real-world deployment notes are always appreciated. 💬

You can also review the complete set of changes in the [full changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.79...v8.4.80).