model
Model measured at 9.81s warm average and 10.41 tok/s, slower than the 120B-A12B Nemotron build despite far fewer parameters; followed the format.
Blog vs Bytecode, a 28-item Kaggle benchmark, graded empty proxy responses as wrong and scored DeepSeek-R1 at 17% until a second gateway showed 100%. Once capture was fixed, frontier models lost points by flagging sound code, while a small Gemma model missed most of the planted flaws.
Reality
The accelerator is in full production and the headline number is a single-request generation rate at 100,000 tokens of context. That is a different purchase order than throughput.
Perspective Coverage
3 publishersReality
Groq 3 LPX is in full production with Nebius as the named first customer. The benchmark is one model at one context length, and the 4x claim does not quite get from hours to minutes.
Reality
NVIDIA's dense-versus-MoE explainer uses Nemotron 3.5 Lightning to walk through per-layer routing. Its own text puts the throughput number and the memory number on two different parameter counts.
Reality
The first third-party benchmark of the LP30 rack came in at roughly four times the next-fastest public endpoint, measured one request at a time on a model small enough to fit.
Reality
A single-box test in Japan put 76 tokens/s next to 4.4 tokens/s, then found the deciding variable elsewhere: which models held the output format and which invented reassurance.
Reality