NVIDIA's Groq 3 LPX hits full production, record 3,400 tokens/s, Nebius first adopter
haider1 · x · 2026-08-25
NVIDIA officially announced that Groq 3 LPX, its interactive AI inference accelerator, is now in full production. An extension of the Vera Rubin NVL72 platform, it delivers ultrafast token generation for latency-sensitive agentic workloads, with Nebius as the first AI cloud to adopt it.
Key numbers: in Artificial Analysis benchmarking it set a record 3,400 output tokens per second running Gemma 4 31B (an open-source agentic model) with a 100,000-token context — the fastest ever recorded for that model. It enables agentic tasks like coding in minutes instead of hours, with 4x faster agent responsiveness.
Context: agentic systems generate massive token volumes across hundreds or thousands of inference steps, so token-generation speed directly determines how fast agents can reason and act in real time.
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