# New Release: Ultralytics v8.4.75

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-75/2081>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [June 22, 2026, 2:54pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-75/2081 "2026-06-22T14:54:52Z")\
**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 22, 2026, 2:54pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-75/2081/1 "2026-06-22T14:54:52Z")

</div>

## 🚀 Ultralytics v8.4.75 Released

**Quick summary:** Ultralytics `v8.4.75` is a small but high-impact release focused on **CoreML reliability and speed on macOS** 🍎⚡. CoreML models now use the **CPU + Neural Engine** path by default on supported Macs, avoiding a crash-prone setting and delivering a much smoother local inference experience for Ultralytics YOLO exports such as YOLO26 and YOLO11.

## 🌟 Highlights

- 🚑 **Major CoreML stability fix for macOS**
- ⚡ **Apple Neural Engine now used by default** on supported Macs
- 🛡 **Automatic fallback for older macOS versions**
- 📝 **Updated docs** explaining the new CoreML behavior
- ✅ **No new model architecture changes** — this release is all about backend reliability and performance

## New Features

### 🍎 CoreML now defaults to CPU + Neural Engine on macOS

In `v8.4.75`, the CoreML backend now loads models with `ComputeUnit.CPU_AND_NE` instead of the previous default behavior.

This change is especially important because certain CoreML execution paths on macOS could trigger hard Python crashes with errors like `MLIR pass manager failed`. By switching to the CPU + Neural Engine path, Ultralytics improves both **stability** and **performance** for local Mac inference.

### ⚡ Faster inference on supported Apple hardware

On macOS 13 and newer, CoreML inference now automatically uses the **Neural Engine** when available. Reported results show roughly:

- **2.5 ms on Neural Engine**
- **8.5 ms on CPU**

That’s about a **3x speedup** , which is a great improvement for real-time and interactive applications.

## Improvements

### 🛡 Better compatibility on older macOS versions

If `CPU_AND_NE` is not supported on the host system, Ultralytics now falls back to `CPU_ONLY` instead of failing. This makes CoreML deployment more dependable across a wider range of Mac environments.

### 📝 Clearer CoreML documentation

The CoreML integration docs were updated to explain the new macOS behavior and why avoiding the GPU path currently improves stability. This should make troubleshooting and deployment much easier for Apple Silicon users.

## Bug Fixes

### 🔧 Fixes crash-prone CoreML execution paths on Mac

Before this release, running a CoreML `.mlpackage` from Python on macOS could crash outright in some environments. With `v8.4.75`, that workflow should now work out of the box on supported Macs with a much more reliable default configuration.

## Pull Requests

- **Run CoreML on the Neural Engine (`CPU_AND_NE`) on macOS hosts** by [@glenn-jocher](https://github.com/glenn-jocher) in [PR #24885](https://github.com/ultralytics/ultralytics/pull/24885)

## Impact

This release will be especially useful if you are:

- Running exported CoreML YOLO models locally on a Mac
- Using Apple Silicon for Python-based inference
- Deploying Ultralytics YOLO models such as [YOLO26 on Ultralytics Platform](https://platform.ultralytics.com/ultralytics/yolo26) or [YOLO11 on Ultralytics Platform](https://platform.ultralytics.com/ultralytics/yolo11)
- Looking for a more stable and faster `.mlpackage` inference experience

While this is not a new model release, it’s an important quality-of-life update for Mac users and should make CoreML workflows much more dependable 🚀

## Try It Out

Update with:

```bash
pip install -U ultralytics

```

Then test your existing CoreML export workflow and let us know how it performs on your Mac.

You can explore the release in the [Ultralytics `v8.4.75` release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.75), and review everything included in the [full changelog for `v8.4.75`](https://github.com/ultralytics/ultralytics/compare/v8.4.74...v8.4.75).

## Feedback

Please give `v8.4.75` a try and share your results, especially if you’re running CoreML inference on Apple Silicon. Feedback from the community helps the Ultralytics team keep improving the experience for everyone 🙌