inference/research
verifiedhigh · 0.85updated 2026-10-14

MLPerf v6.0 Intel 4x Intel Arc Pro B70: gpt-oss-120b Offline aggregate tok/s

1536.9 output tokens/s (aggregate over 4 accelerators, Offline)

Fields

id
benchmarks/mlperf-v6-0-intel-4xarcb70-gptoss-120b-gpt-oss-120b-offline
Metric
tps_aggregate
Value
1,536.9
Unit
output tokens/s (aggregate over 4 accelerators, Offline)
Model
gpt-oss-120b
Methodology
VENDOR-SUBMITTED MLPerf Inference v6.0 closed division, Datacenter suite, Offline scenario. Intel 1-node-4x-BMG-B70: 4x Intel Arc Pro B70. Framework PyTorch vLLM. 'Tokens/s' = AGGREGATE output-token throughput across the 4 accelerators (NOT per-request). Value verbatim from summary_results.json. min_query_count/min_duration per MLPerf rules; binding latency constraint applies to Server/Interactive.
Measured by
vendor
Reproducible
yes

Cross-references

Accelerators (1)

Engine (1)