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

MLPerf Inference v6.0 — Intel 1-node-4x Arc Pro B70 (BMG), llama2-70b / llama3.1-8b / gpt-oss-120b, vLLM

benchmark

Fields

id
sources/bench-mlperf-v6-0-intel-4x-bmg-b70
URL
https://github.com/mlcommons/inference_results_v6.0/tree/main/closed/Intel/results/1-node-4x-BMG-B70
Publisher
MLCommons / Intel
Kind
benchmark
Accessed
2026-10-14
notes
Closed-division submission. 4x Arc Pro B70 32GB on Xeon 698X host, PyTorch vLLM, PCIe Gen5 x16. Offline + Server tokens/sec verbatim from mlperf_log_summary.txt.

Notes

Closed-division submission. 4x Arc Pro B70 32GB on Xeon 698X host, PyTorch vLLM, PCIe Gen5 x16. Offline + Server tokens/sec verbatim from mlperf_log_summary.txt.

Cross-references

This record references no other records.