Skip to content
Working Knowledge
GuideReferenceWorkbenchBoardNotesAbout
Search⌘K

Browse categories

The Reference

01The Big Picture02Model Architectures03How Models Learn04How Models Run05Getting Models to Act06Language & Perception07Measuring Models08Safety & Alignment09Hardware & Infrastructure10Version Control11The Command Line12Databases & SQL13Environments & Packaging14Shipping & Collaboration15The Workbench
09 · Hardware & Infrastructure

NPU

Neural Processing Unit

InterInvestors

A small AI-accelerator chip built into consumer devices (phones, laptops) to run models locally without the cloud.

Concrete example

On-device features like live photo edits or offline voice typing run on the NPU in your phone.

Nearby in Hardware & Infrastructure

HBMHigh Bandwidth MemoryMFUModel FLOPs UtilizationNVLink / InfiniBandHigh-speed GPU interconnectsTCOTotal Cost of Ownership
Previous term← NoSQLNext termnpx →

AtlasScope

I explain technical systems in plain English—and build practical tools for using them.

Read the guideBrowse the referenceWhat Atlas is doing now

Contact & collaboration

GitHub ↗
Working Knowledge · A practical field guideBuilt and maintained by Atlas
HomeGuideSearchWorkbenchMore