NVIDIA's Groq 3 LPX enters full production, hits 3,400 tokens/sec in tests
zephyr_z9 · x · 2026-08-24
NVIDIA says Groq 3 LPX, its low-latency inference accelerator designed to extend Vera Rubin NVL72, is now in full production.
In Artificial Analysis testing, Groq 3 LPX reached 3,400 output tokens/sec running Gemma 4 31B with a 100K-token context; NVIDIA claims 4x faster responsiveness than the nearest alternative for latency-sensitive agentic workloads.
The architecture splits inference between Rubin GPUs for large-scale context processing and LPX for fast token generation, targeting coding agents, multi-step reasoning, and tool-use workloads. Nebius will be the first AI cloud to deploy it via Nebius Token Factory.
More from Infra
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16
- Fastino launches Training API for SFT/RL, claiming 25-85% cost cut vs Tinker — kalyan_kpl · 2026-10-16