Fact · Speech recognition
38trillion operations per second
Apple says the Neural Engine in its M4 chip can reach up to 38 trillion operations per second, faster than the neural processing unit of any AI PC at the time.
Checked against its source on October 17, 2026
In the source's own words
“capable of up to 38 trillion operations per second, which is faster than the neural processing unit of any AI PC today”
Apple introduces M4 chip, Apple, Apple Newsroom, 2024, Neural Engine paragraph.
Open the original- What it measures
- The Neural Engine is the dedicated block in Apple silicon that runs machine learning models such as speech recognition. The figure is a peak rate for the chip, not a measured speech recognition speed.
- What it does not show
- Apple's own claim, stated as a peak. The comparison is with AI PC neural processing units as of May 2024.