AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

llama2-70b-99.9 — Interactive — Cisco_UCS_H200x8_MI350Xx8_G200_2x2_TOR

MLCommons MLPerf · observation · Publication date unknown

70354.5 Tokens/s; MLPerf v6.1, closed.

Read original source ↗ Open in workspace

recordType
benchmark
region
Global
value
70354.5
unit
Tokens/s
dimensions
{"division":"closed","location":"./closed/Cisco/results/Cisco_UCS_H200x8_MI350Xx8_G200_2x2_TOR/llama2-70b-99.9/Interactive/performance/run_1","metric":"Performance_Result","model":"llama2-70b-99.9","precision":"fp8,fp4","release":"v6.1","scenario":"Interactive","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.