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
04 · How Models Run

TTFT

Time To First Token

InterOperators

How long after you hit enter before the first word appears. A core latency metric — low TTFT feels responsive.

Concrete example

The pause before a chatbot starts typing back at you.

Nearby in How Models Run

TokenThe unit a model reads & writesTPSTokens Per Second
Previous term← TransformerNext termTTS →

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