# NVIDIA and Inferact submit initial vLLM Rubin NVL72 benchmark result

> Original title: BREAKING NEWS: Less than 3 weeks since the MiniMax M3.1 Flash launch, NVIDIA and @Inferact have already submitted an initial vLLM Rubin N...

- Source: SemiAnalysis
- Published: 2026-11-12T03:40:15.000Z
- Bad Influence: https://badinfluence.news/items/cuhq4nyvehennrv48n0laqxyn
- Original: https://x.com/SemiAnalysis_/status/2120723320890925142

## Summary

NVIDIA and Inferact have submitted an initial vLLM benchmark on Rubin NVL72 that the post calls state-of-the-art, with 6.5x better performance per TCO than GB300 NVL72. The submission uses a new locality-aware MoE feature in CUDA 13.4, which the post says reduces latency and increases realized HBM bandwidth by about 1.2x.

## Post

BREAKING NEWS: Less than 3 weeks since the MiniMax M3.1 Flash launch, NVIDIA and @Inferact have already submitted an initial vLLM Rubin NVL72 submission that is state-of-the-art and delivers 6.5x better perf per TCO than GB300 NVL72.

Great to see that Rubin is already becoming more and more mature and integrated in partnership with @vllm_project!

This Rubin submission uses the new locality-aware MoE feature in CUDA 13.4, which reduces latency and increases realized HBM bandwidth by ~1.2x.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW5Sn0MXYAAR1QW.jpg&mode=thumb&exp=1794700800&sig=787ff6e1d6c278bc)