AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

llama3.1-8b-edge — SingleStream — HPE_PROLIANT_DL345_GEN12_RTX_PRO_4500_PCIE_32GBx4_TRT_open

MLCommons MLPerf · observation · Publication date unknown

1203.785699 Latency (ms); MLPerf v6.1, open.

Read original source ↗ Open in workspace

recordType
benchmark
region
Global
value
1203.785699
unit
Latency (ms)
dimensions
{"division":"open","location":"./open/HPE/results/HPE_PROLIANT_DL345_GEN12_RTX_PRO_4500_PCIE_32GBx4_TRT_open/llama3.1-8b-edge/SingleStream/performance/run_1","metric":"Performance_Result","model":"llama3.1-8b-edge","precision":"fp4","release":"v6.1","scenario":"SingleStream","submissionId":null,"submitter":"HPE","suite":"edge","system":"HPE_PROLIANT_DL345_GEN12_RTX_PRO_4500_PCIE_32GBx4_TRT_open","unit":"Latency (ms)"}

Evidence & attribution

MLCommons, MLPerf Inference v6.1, published submission results. Metadata adapted; scenarios and units remain separate.

License: Apache-2.0

First collected: 2026-09-19T22:50:59.123Z. This is not the publication date.