NVIDIA Groq 3 LPX hits 3,431 tokens/s on Gemma 4 31B in Artificial Analysis benchmarks
ArtificialAnlys · x · 2026-08-25
Artificial Analysis benchmarked an early private deployment of NVIDIA's Groq 3 LPX 'interactive AI inference' rack—now in full-scale production and entering operation later this year—serving Gemma 4 31B. At both 10k and 100k input lengths, the endpoint delivered a median output speed of 3,400 tokens/s over 50 sequential requests, the highest 100k-context output speed measured for the model, with speed maintained across long contexts.
More from Infra
- Jensen Huang joins BG2 podcast: does AI revenue justify capex, '27 bottlenecks — elonmusk · 2026-10-16
- Mistral's on-device infra rack revealed: DGX Spark, Mac Studio and more — gregmushen · 2026-10-16
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Cerebras pushes disaggregated inference: heterogeneous prefill pools feeding wafer-scale decode — ai · 2026-10-16