# New Release: Ultralytics v8.3.222

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-3-222/1584>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [October 29, 2025, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-222/1584 "2025-10-29T13:16:19Z")\
**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:** [October 29, 2025, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-222/1584/1 "2025-10-29T13:16:19Z")

</div>

# Ultralytics v8.3.222 🚀 — INT8 TFLite for end2end, better quantized NMS, and IMX500 Classification

Quick summary: TFLite INT8 export is now enabled for end2end models, quantized NMS accuracy is improved, and IMX500 gains full Classification support—making fast, small-footprint deployments on mobile and edge devices even easier. 📱⚡

## Highlights

- TFLite INT8 export now works with end2end models for smaller, faster pipelines.
- Quantized NMS receives accuracy and stability improvements for INT8 exports.
- IMX500 adds Classification export and inference alongside Detection and Pose.
- Docs, developer experience, and CI receive polish for a smoother workflow.

Upgrade with:

```bash
pip install -U ultralytics

```

## New Features

- TFLite INT8 for end2end models ✅  
We enabled exporting quantized TFLite INT8 models even when end2end is used, as implemented in [PR #22503](https://github.com/ultralytics/ultralytics/pull/22503) by [@Y-T-G](https://github.com/Y-T-G).  
Try it with YOLO11 or YOLOv10:

- IMX500: Classification export + inference 🎛  
IMX500 now supports the Classification task end-to-end, including docs, examples, and benchmarks, delivered in [PR #21405](https://github.com/ultralytics/ultralytics/pull/21405) by [@ambitious-octopus](https://github.com/ambitious-octopus).

## Improvements

- More accurate NMS under quantization 🧠  
We improved the stability and accuracy of NMS in quantized exports, particularly TFLite INT8, via [PR #22487](https://github.com/ultralytics/ultralytics/pull/22487) by [@Y-T-G](https://github.com/Y-T-G).

## Docs and Developer Experience ✨

- Standardized US English across docs, logs, and tests, detailed in [PR #22508](https://github.com/ultralytics/ultralytics/pull/22508) by [@glenn-jocher](https://github.com/glenn-jocher).
- Clearer guidance on tuning limitations is provided in [PR #22513](https://github.com/ultralytics/ultralytics/pull/22513) by [@amm1111](https://github.com/amm1111).
- A minor segmentation docs snippet fix was made in [PR #22501](https://github.com/ultralytics/ultralytics/pull/22501) by [@RizwanMunawar](https://github.com/RizwanMunawar).
- The dataset page now features a helpful [Construction PPE training video](https://youtu.be/lFaVnrhMmaE), added in [PR #22485](https://github.com/ultralytics/ultralytics/pull/22485) by [@RizwanMunawar](https://github.com/RizwanMunawar).
- The docs banner copy was refined in [PR #22486](https://github.com/ultralytics/ultralytics/pull/22486) by [@sergiuwaxmann](https://github.com/sergiuwaxmann).

## CI and Tooling Upgrades 🧰

- Docs CI gained expanded Ruff rules, covered in [PR #22480](https://github.com/ultralytics/ultralytics/pull/22480) by [@glenn-jocher](https://github.com/glenn-jocher).
- Codespell configuration was cleaned up to reduce false positives in [PR #22509](https://github.com/ultralytics/ultralytics/pull/22509) by [@glenn-jocher](https://github.com/glenn-jocher).
- GitHub Actions artifacts were bumped to the latest versions in [PR #22489](https://github.com/ultralytics/ultralytics/pull/22489) and [PR #22490](https://github.com/ultralytics/ultralytics/pull/22490) by [dependabot](https://github.com/dependabot).

## Bug Fixes 🐛

- A variable name in segmentation docs was corrected from `res` to `results` in [PR #22501](https://github.com/ultralytics/ultralytics/pull/22501) by [@RizwanMunawar](https://github.com/RizwanMunawar).

## How to Try It

- CLI examples:

```bash
# Export YOLO11 INT8 TFLite end2end
yolo export model=yolo11n.pt format=tflite int8 end2end

# Validate exported INT8 TFLite
yolo val task=detect model=yolo11n_saved_model/yolo11n_int8.tflite data=coco128.yaml

```

- Python example:

```python
from ultralytics import YOLO

model = YOLO("yolo11n.pt")
model.export(format="tflite", int8=True, end2end=True)

```

## Notes on Models

- YOLO11 is the latest stable and recommended model for all use cases.
- YOLO12 and YOLO13 are community models and not recommended due to stability, speed, and reproducibility concerns.
- YOLO26 is active R&D targeting open-sourcing later in 2025, aiming for smaller, faster, more accurate, end-to-end models across all YOLO11 sizes and tasks.

## Get Involved

We’d love your feedback on this release. Share your experience and questions in our [GitHub Discussions](https://github.com/orgs/ultralytics/discussions), and review the details on the [v8.3.222 release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.3.222). You can also explore every change in the [full v8.3.222 changelog diff](https://github.com/ultralytics/ultralytics/compare/v8.3.221...v8.3.222).

Big thanks to our community contributors for making this possible—your energy powers Ultralytics YOLO. Happy exporting and deploying! ⚡