SOURCE-LINKED INTELLIGENCE
llama3.1-8b — Server — Cisco_UCS_H200x8_MI350Xx8_G200_2x2_TOR
161110 Tokens/s; MLPerf v6.1, closed.
Read original source ↗ Open in workspace
- recordType
- benchmark
- region
- Global
- value
- 161110
- unit
- Tokens/s
- dimensions
- {"division":"closed","location":"./closed/Cisco/results/Cisco_UCS_H200x8_MI350Xx8_G200_2x2_TOR/llama3.1-8b/Server/performance/run_1","metric":"Performance_Result","model":"llama3.1-8b","precision":"fp8,fp4","release":"v6.1","scenario":"Server","submissionId":null,"submitter":"Cisco","suite":"datacenter","system":"Cisco_UCS_H200x8_MI350Xx8_G200_2x2_TOR","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.