Inference Chip Index

← All slices

gpt-oss-120b · Server

gpt-oss-120b / Server / Tokens/s

v6.0|closed|gpt-oss-120b|Server|Tokens/s|official-system

Metric: Performance_Result (Tokens/s) · winning: higher · 28 ranking-eligible rows · vendors 3 · families 7 · never mixed with other slices

All systems (official)
RankPerformanceUnitSystemSubmitterAcceleratorSource
11,096,770.0000Tokens/sNebius GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT)NebiusNVIDIA GB300source
21,072,250.0000Tokens/sNVIDIA GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT)NVIDIANVIDIA GB300source
3956,523.0000Tokens/sCoreWeave GB300 NVL72 (64x GB300-288GB_aarch64, TensorRT)CoreWeaveNVIDIA GB300source
4900,054.0000Tokens/sAMD MI355X Custom ClusterAMDAMD Instinct MI355X 288GB HBM3e (x94)source
5899,218.0000Tokens/sNVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT)NVIDIANVIDIA GB200source
6743,550.0000Tokens/sCoreWeave GB200 NVL72 (64x GB200-186GB_aarch64, TensorRT)CoreWeaveNVIDIA GB200source
7110,655.0000Tokens/sCisco UCS C880A M8 (8x NVIDIA B300-SXM-270GB, TensorRT)CiscoNVIDIA B300-SXM-270GBsource
8106,397.0000Tokens/sG894-SD3-AAX7GigaComputingNVIDIA B300-SXM-270GBsource
9100,687.0000Tokens/sThinkSystem SR680a V4 (8x B300-SXM-270GB, TensorRT)LenovoNVIDIA B300-SXM-270GBsource
10100,656.0000Tokens/sXA NB3I-E12ASUSTeKNVIDIA B300-SXM-270GBsource
11100,437.0000Tokens/sNebius B300 n1 (8x B300-SXM-270GB, TensorRT)NebiusNVIDIA B300-SXM-270GBsource
12100,328.0000Tokens/sNVIDIA DGX B300 (8x B300-SXM-270GB, TensorRT)NVIDIANVIDIA B300-SXM-270GBsource
1387,444.2000Tokens/sNebius B200 n1 (8x B200-SXM-180GB, TensorRT)NebiusNVIDIA B200-SXM-180GBsource
1482,136.1000Tokens/ssmci355-ccs-aus-m09-17 (AS -4126GS-NMR-LCC)AMDAMD Instinct MI355X 288GB HBM3esource
1580,089.6000Tokens/sG893-ZX1-AAX4GigaComputingAMD Instinct MI355X 288GB HBM3esource
1678,603.5000Tokens/sPowerEdge XE9785L (8x MI355X)DellAMD Instinct MI355X 288GB HBM3esource
1778,186.3000Tokens/sBM.GPU.MI355X.8ORACLEAMD Instinct MI355X 288GB HBM3esource
1875,354.9000Tokens/sHPE ProLiant Compute XD685 (8x AMD Instinct MI355X 288GB, vLLM)HPEAMD Instinct MI355X 288GB HBM3esource
1971,588.1000Tokens/sLLM-D v0.5.0,Openshift 4.20.12,NVIDIA 8xB200-SXM-180GBRedHatNVIDIA B200-SXM-180GBsource
2053,462.7000Tokens/sNVIDIA GB300 NVL72 (4x GB300-288GB_aarch64, TensorRT)Lambda_SITNVIDIA GB300source
2124,103.2000Tokens/sLLM-D v0.5.0,OpenShift 4.21,IBM cloud gx3d-160x1792x8h200,NVIDIA 8xH200-SXM-141GBRedHatNVIDIA H200-SXM-141GBsource
2217,737.6000Tokens/sHPE ProLiant Compute DL380a Gen12 (10x NVIDIA RTX PRO 6000 Blackwell Server Edition, TensorRT)HPENVIDIA RTX PRO 6000 Blackwell Server Editionsource
2314,973.1000Tokens/sNebius GB300 NVL72 (4x GB300-288GB_aarch64, TensorRT)NebiusNVIDIA GB300source
2414,258.9000Tokens/sHPE ProLiant Compute DL380a Gen12 (8x NVIDIA RTX PRO 6000 Blackwell Server Edition, TensorRT)HPENVIDIA RTX PRO 6000 Blackwell Server Editionsource
256,687.2500Tokens/sHPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, TensorRT)HPENVIDIA RTX PRO 6000 Blackwell Server Editionsource
26951.6740Tokens/s1-node-4x-BMG-B70IntelIntel(R) Arc Pro(R) B70source
27884.2380Tokens/s1-node-4x-BMG-Pro-B60-DualIntelMS-Intel Arc Pro B60 Dual 48G Turbosource
28452.1910Tokens/s1-node-4x-BMG-B60IntelIntel(R) Arc Pro(R) B60source