Skip to content Black FridayUp to 76% off Vitals, Levers and SoundBar, until 5 December
Vitals · GPU and Neural Engine

See GPU and Neural Engine usage on your Mac, by app

Vitals has a tab for the GPU and a tab for the Neural Engine. Each shows how hard the chip is working, which apps are using it and a chart of the last minutes. Both can also be menu bar items and cards on the Overview.

The Vitals Neural tab: how hard the 16-core Neural Engine is working, its memory traffic, average and peak, and the apps holding it open: Photos, Xcode and Safari

The GPU tab

The GPU tab shows how busy the GPU is, its memory, the average and the peak, and the apps using it with the heaviest first. A render, a game or a browser tab shows up under its own name. The chart covers the last 5, 15 or 30 minutes.

A card names the top app, and the list under it gives each app’s share of the GPU with its process count.

The GPU’s temperature is with the other sensors. The GPU is also in the history, so a render from an hour ago is still there to see. Activity Monitor has a GPU column and a GPU History window.

The Vitals GPU tab on an Apple M2 Max: GPU use charted over time, memory, average and peak, and the apps using the GPU with Figma first

A number for the Neural Engine

On Apple silicon the Neural Engine does real work, for Photos, Spotlight, dictation and on-device models, and Activity Monitor shows nothing for it. Vitals works out how hard it is working from the memory it moves, against the most this Mac has ever moved.

macOS does not say which app is working the Neural Engine, only which apps hold it open. Those are the apps Vitals names. The tab exists on Macs with Apple silicon. An Intel Mac has no Neural Engine and no tab.

The tab shows the percentage with its average and peak, the memory traffic behind the figure, and each app with the number of connections it holds. Work that used to be invisible, such as Photos indexing a library overnight, now has a name and a chart.

The Neural Engine at 34% on 16 cores, with Photos and macOS holding it open, and a notice that Photos has kept it busy for 20 minutes

Local models run on the GPU

Models run with PyTorch or MLX use the GPU, not the Neural Engine. An Ollama session therefore shows as a busy GPU and a quiet Neural Engine. That is correct, and surprising the first time. Ollama’s memory is listed under Ollama, where you would look for it.

So if you are checking whether a local model is using the chip, look at the GPU tab. A quiet Neural Engine during a model run does not mean something is wrong.

A GPU card at 91% with Ollama using 6.2 GB beside a Neural Engine card at 2%, with a note that PyTorch and MLX run on the GPU

Both can be menu bar items, as a number, a graph or both, in whatever order you like, and each has a card on the Overview. That is enough to keep an eye on a long render without opening anything.

The GPU reading turns red at 90% in the menu bar. Vitals also sends a notice when an app has kept the Neural Engine busy for twenty minutes.

How to use it

  1. 1

    Open the GPU tab

    See how busy the GPU is, its memory, the average and peak, and the apps using it.

  2. 2

    Open the Neural Engine tab

    On a Mac with Apple silicon, see how hard it is working and which apps hold it open.

  3. 3

    Add them to the menu bar

    In Settings → Layout → Menu Bar, add a GPU item and a Neural Engine item as a number or a graph.

The details

GPU tab
Use, memory, average and peak, with the apps using it
Neural Engine tab
How hard it is working and the apps that hold it open, on Apple silicon
Charts
The last 5, 15 or 30 minutes
How the Neural Engine is measured
The memory it moves, against the most this Mac has moved
Menu bar
An item for each; the GPU turns red at 90%
Notice
When an app keeps the Neural Engine busy for twenty minutes

Questions

Does Vitals show Neural Engine usage?

Yes, on Macs with Apple silicon: how hard it is working, which apps are using it, and a chart of the last minutes.

Why does my local model not show on the Neural Engine?

Models run with PyTorch or MLX use the GPU, not the Neural Engine. They show on the GPU tab.

How does Vitals measure the Neural Engine?

From the memory it moves, compared with the most this Mac has ever moved. macOS does not say which app is working it, only which apps hold it open, and those are the ones Vitals names.

Does it show GPU memory?

Yes, with the GPU’s use, average and peak, and the apps using it.

Does Activity Monitor show this?

It has a GPU column and a GPU History window, and nothing for the Neural Engine.

The same feature on the app's own site: vitalsmac.com/features/gpu-and-neural-engine

Find the app behind every number.