HWBench

Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)): edge AI benchmarks

Vendor Dell_MangoBoostForm factor datacenter serverCompute GPUIndicative price unknownPower envelope unknownPublished rows 2

Key results

Best published result per workload for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8))
WorkloadBest resultModel · precisionPower · perf/WGrade · dateSource
LLM serving (MLPerf datacenter)285454 tok/s
batch unknown		MLPerf gpt-oss-120b
fp8 · ROCm		unknownA 2026-09-16 (published)MLPerf Inference v6.1, closed division, data-centre suite

Best published result per workload, across model sizes. For like-for-like groups, open the per-workload tables below.

Show data — per-workload tables

object detection

◌

No published object detection results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

instance segmentation

◌

No published instance segmentation results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

◌

No published pose estimation results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

◌

No published image classification results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

◌

No published semantic segmentation results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

◌

No published speech-to-text results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

◌

No published LLM generation results for Heterogeneous Four-Cluster (8x AMD Instinct MI300X 192GB HBM3 (x2x8) and AMD Instinct MI355X 288GB HBM3e (x2x8)) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM serving (MLPerf datacenter)

Like-for-like groupBest resultModel · precision · stackGradePowerSource · dateRank in group
LLM >40B · b=unknown285454 tok/sMLPerf gpt-oss-120b
fp8 · ROCm		Aunknown power n/aMLPerf Inference v6.1, closed division, data-centre suite
2026-09-16 (published)		10 of 93
How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.

Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.