SOURCE-LINKED INTELLIGENCE
llama3.1-8b — Server — X215M8_X580P_RTXPro6000_96GBx4_TRT
24498.6 Tokens/s; MLPerf v6.1, closed.
Read original source ↗ Open in workspace
- recordType
- benchmark
- region
- Global
- value
- 24498.6
- unit
- Tokens/s
- dimensions
- {"division":"closed","location":"./closed/Cisco/results/X215M8_X580P_RTXPro6000_96GBx4_TRT/llama3.1-8b/Server/performance/run_1","metric":"Performance_Result","model":"llama3.1-8b","precision":"fp4","release":"v6.1","scenario":"Server","submissionId":null,"submitter":"Cisco","suite":"datacenter","system":"X215M8_X580P_RTXPro6000_96GBx4_TRT","unit":"Tokens/s"}
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.