SOURCE-LINKED INTELLIGENCE
qwen3-vl-235b-a22b — Server — G894-ZD3-AAX7_B300-SXM-270GBx8_TRT
115.7839399384 Queries/s; MLPerf v6.1, closed.
Read original source ↗ Open in workspace
- recordType
- benchmark
- region
- Global
- value
- 115.7839399384
- unit
- Queries/s
- dimensions
- {"division":"closed","location":"./closed/GigaComputing/results/G894-ZD3-AAX7_B300-SXM-270GBx8_TRT/qwen3-vl-235b-a22b/Server/performance/run_1","metric":"Performance_Result","model":"qwen3-vl-235b-a22b","precision":"NVFP4 weights with FP8 KV cache","release":"v6.1","scenario":"Server","submissionId":null,"submitter":"GigaComputing","suite":"datacenter","system":"G894-ZD3-AAX7_B300-SXM-270GBx8_TRT","unit":"Queries/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.