Checked fact 519417 Nov 2026Research
Nvidia's developer blog describes Vera Rubin NVL72 as generally available through cloud infrastructure partners; it says reruns with a newer software stack for Llama 3.1 8B, gpt-oss 20B and DLRMv4 are not MLCommons-verified and not part of the official results.
the company says This is the company's own statement about itself, not something we found out ourselves.
The exact words it rests on
Vera Rubin NVL72 systems are generally available through cloud infrastructure partners worldwide. ... These are unverified results rather than MLCommons submissions
What the source said when we opened it, on 16 Nov 2026.
The source
NVIDIA Vera Rubin NVL72 Achieves up to 2x Blackwell Ultra Performance in MLPerf Training v6.1
Checked
Checked by the notis newsroom on , against the source above.
In the story
Nvidia says Vera Rubin NVL72 trained DeepSeek-V3 in 4.14 minutes on 1,024 GPUs 17 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.