Zum Hauptinhalt springen
•
Windows Tipps & SecurityWindows 11: Die neue Suche öffnet jetzt Android-Apps vom Smartphone(01.11.2026 um 13:00 Uhr)
••
Sicherheitslücken (CVE)CVE-2026-105483 remediation checklist for Node.js teams(01.11.2026 um 21:40 Uhr)
••
Sichere ProgrammierungThe Hard Part of Leaving `request` is the App Built Around It(01.11.2026 um 21:41 Uhr)
•
Sichere ProgrammierungGiving an AI agent a wallet without giving it your keys(01.11.2026 um 21:41 Uhr)
•••
Proof of Concept (PoC)Pasta Inspector(01.11.2026 um 21:48 Uhr)
••
Windows Tipps & SecurityWindows 11: Die neue Suche öffnet jetzt Android-Apps vom Smartphone(01.11.2026 um 13:00 Uhr)
••
Sicherheitslücken (CVE)CVE-2026-105483 remediation checklist for Node.js teams(01.11.2026 um 21:40 Uhr)
••
Sichere ProgrammierungThe Hard Part of Leaving `request` is the App Built Around It(01.11.2026 um 21:41 Uhr)
•
Sichere ProgrammierungGiving an AI agent a wallet without giving it your keys(01.11.2026 um 21:41 Uhr)
•••
Proof of Concept (PoC)Pasta Inspector(01.11.2026 um 21:48 Uhr)
•
Intelligence View
⚡ tsecurity.de Intelligence

Tokens per second is a memory bandwidth number. Measure it in 2 seconds.

A 40B model that does 125 tok/s on a laptop, and a 7B model that does 1.5 tok/s on a 2011 CPU with the same amount of RAM. Same ballpark of memory, ~80× …

Beitrag
0
Seite
0
↗ Quelle (DEV Community)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!

A 40B model that does 125 tok/s on a laptop, and a 7B model that does 1.5 tok/s on a 2011 CPU with the same amount of RAM. Same ballpark of memory, ~80× difference in speed. Almost every explanation you will read for that gap is wrong, and the wrong explanation costs people money. Here is the number that actually decides it: how many bytes your... Weiterlesen: Tokens per second is a memory bandwidth number. Measure it in 2 seconds.

Intelligence Digest gratis Dagelijks het belangrijkste beveiligingsnieuws · kan op elk moment worden opgehaald
Community Rating & Social Proof
⭐ Leser-Wertung
–
Ø / 5.0
Nog geen recensies van lezers
Was deze pagina nuttig?
0
Jetzt Bewertung abgeben
🟢 Niedrig (1-3.9) 🟡 Mittel (4.0-6.9) 🔴 Hoch (7.0-8.9) Kritisch (9.0-10.0)

Verwant Story Cluster & Sources (vector AI)

Trek om te vernieuwen
Nächster Beitrag