SOURCE-LINKED INTELLIGENCE
llama2-70b-99.9 — Server — G894-ZD3-AAX7_B300-SXM-270GBx8_TRT
114578 Tokens/s; MLPerf v6.1, closed.
Read original source ↗ Open in workspace
- recordType
- benchmark
- region
- Global
- value
- 114578
- unit
- Tokens/s
- dimensions
- {"division":"closed","location":"./closed/GigaComputing/results/G894-ZD3-AAX7_B300-SXM-270GBx8_TRT/llama2-70b-99.9/Server/performance/run_1","metric":"Performance_Result","model":"llama2-70b-99.9","precision":"fp4","release":"v6.1","scenario":"Server","submissionId":null,"submitter":"GigaComputing","suite":"datacenter","system":"G894-ZD3-AAX7_B300-SXM-270GBx8_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.