inference/research
verifiedhigh · 0.90updated 2026-10-03

MLPerf Inference v6.1 closed results: Intel 4x Arc Pro B70 Llama2-70B Offline summary log

benchmark

Fields

id
sources/bench-intel-arc-pro-b70-mlperf-v6-1-llama2-70b
URL
https://raw.githubusercontent.com/mlcommons/inference_results_v6.1/main/closed/Intel/results/1-node-4x-BMG-B70/llama2-70b-99.9/Offline/performance/run_1/mlperf_log_summary.txt
Publisher
MLCommons / Intel
Kind
benchmark
Accessed
2026-10-03
notes
MLPerf Inference v6.1 raw performance log for Intel Arc Pro B70 (1-node-4x-BMG-B70) running llama2-70b-99.9 Offline. Result: 2,464.98 tokens/sec, 8.48 samples/sec. VALID result.

Notes

MLPerf Inference v6.1 raw performance log for Intel Arc Pro B70 (1-node-4x-BMG-B70) running llama2-70b-99.9 Offline. Result: 2,464.98 tokens/sec, 8.48 samples/sec. VALID result.

Cross-references

This record references no other records.