inference/research
verifiedlow · 0.50updated 2026-10-14

MLPerf Inference v4.1 (open) — HPE DL380a 4x H100 NVL, Mixtral-8x7B, TensorRT

benchmark

Fields

id
sources/bench-mlperf-v4-1-hpe-4xh100nvl-mixtral
URL
https://github.com/mlcommons/inference_results_v4.1/tree/main/open/HPE/results/HPE_ProLiant_DL380a_H100_NVL_94GBx4_TRT
Publisher
MLCommons / HPE
Kind
benchmark
Accessed
2026-10-14
notes
Open-division submission logs. Mixtral-8x7B Offline, tokens/sec verbatim. Aggregate across 4x H100-NVL-94GB.

Notes

Open-division submission logs. Mixtral-8x7B Offline, tokens/sec verbatim. Aggregate across 4x H100-NVL-94GB.

Cross-references

This record references no other records.