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

MLPerf Inference v5.1 — Intel 1-node-4x Arc Pro B60 Dual, llama2-70b / llama3.1-8b(-edge), vLLM

benchmark

Fields

id
sources/bench-mlperf-v5-1-intel-4x-bmg-pro-b60
URL
https://github.com/mlcommons/inference_results_v5.1/tree/main/closed/Intel/results/1-node-4x-BMG-Pro-B60-Dual
Publisher
MLCommons / Intel
Kind
benchmark
Accessed
2026-10-14
notes
Closed-division submission. 4x Arc Pro B60 Dual GPU, vLLM. Also a 1x single-GPU llama3.1-8b-edge SingleStream run (per-request TTFT/TPOT). tokens/sec verbatim.

Notes

Closed-division submission. 4x Arc Pro B60 Dual GPU, vLLM. Also a 1x single-GPU llama3.1-8b-edge SingleStream run (per-request TTFT/TPOT). tokens/sec verbatim.

Cross-references

This record references no other records.