NVIDIA Groq 3 LPX hits 3,431 tokens/s for Gemma 4 31B in private benchmark
IanAndrewsDC · x · 2026-08-25
NVIDIA announced that the Groq 3 LPX 'interactive AI inference' rack is in full-scale production and will enter operation later this year. In a private benchmark by Artificial Analysis running Gemma 4 31B, the system delivered a median output speed of 3,431 tokens/s at 10k and 100k input lengths—the highest speed recorded for this model with a 100k context.
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