Nvidia Groq 3 LPX system hits >3,400 tok/s on small models

Jsevillamol · x · 2026-08-27

Nvidia's Groq 3 LPX system excels at fast decode of small models (>3,400 tok/s) using 128GB of ultrafast SRAM instead of HBM. Nvidia proposes combining LPUs with GPUs to bring this speed to frontier-scale models.

Related event: NVIDIA Groq 3 LPX Hits 3,400+ tok/s Decoding on Small Models(2 posts)→

Original post →

More from Infra

Infra channel →