HWBenchedge-AI hardware data, cited & graded

QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) vs Rockchip RV1109 (NPU)

Quanta_Cloud_Technologydatacenter server · no photo yet
No licensed photo available — placeholder drawing.
Rockchipedge SoC · no photo yet
No licensed photo available — placeholder drawing.

Only QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) has published results here; Rockchip RV1109 (NPU) has none for the workloads we track.

QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB)Rockchip RV1109 (NPU)
Best speech-to-text45408 FPS A
undated
n/a
Powern/an/a
Perf / Wn/an/a
Pricen/an/a
Workloads with data1 of 70 of 7

Best published speech-to-text result per platform. n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

◌

No published object detection results for QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) 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 QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) 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 QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) 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 QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) 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 QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) 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

Only QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) has published speech-to-text results.

PlatformResultModel · precision · stackGradePowerSource
QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB)45408 FPS
throughput_offline · b=unknown
MLPerf whisper
fp16 · TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentM · unknown
Aunknown power n/a
no power published
MLPerf Inference v6.1 (closed, datacenter) ID D75H-10U_B300-270GBx8_TRT
undated

Rockchip RV1109 (NPU):

◌

No published speech-to-text results for Rockchip RV1109 (NPU) or QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) 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 QuantaGrid D75H-10U (8x NVIDIA B300-SXM-270GB) or Rockchip RV1109 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

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.