HWBench

NUCLEO-G0B1RE (STM32G0B1RE): edge AI benchmarks

Vendor BoschForm factor microcontroller / tinyCompute 32-bit Arm® Cortex®-M0+Indicative price unknownPower envelope unknownPublished rows 4

Key results

Best published result per workload for NUCLEO-G0B1RE (STM32G0B1RE)
WorkloadBest resultModel · precisionPower · perf/WGrade · dateSource
tiny image classification0.657 inferences/s
batch 1
ResNet-8 (MLPerf Tiny IC)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
unknownA Older data (2024)MLPerf Tiny v1.2 (closed)
visual wake words0.707 inferences/s
batch 1
MobileNetV1 0.25 (MLPerf Tiny VWW)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
unknownA Older data (2024)MLPerf Tiny v1.2 (closed)
anomaly detection24.45 inferences/s
batch 1
FC autoencoder (MLPerf Tiny AD)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
unknownA Older data (2024)MLPerf Tiny v1.2 (closed)
keyword spotting2.11 inferences/s
batch 1
DS-CNN (MLPerf Tiny KWS)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
unknownA Older data (2024)MLPerf Tiny v1.2 (closed)

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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) 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 NUCLEO-G0B1RE (STM32G0B1RE) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

tiny image classification

Like-for-like groupBest resultModel · precision · stackGradePowerSource · dateRank in group
mid-size CNN · b=10.657 inferences/sResNet-8 (MLPerf Tiny IC)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
Aunknown power n/aMLPerf Tiny v1.2 (closed)
Older data (2024)
19 of 19

visual wake words

Like-for-like groupBest resultModel · precision · stackGradePowerSource · dateRank in group
mobile-class CNN · b=10.707 inferences/sMobileNetV1 0.25 (MLPerf Tiny VWW)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
Aunknown power n/aMLPerf Tiny v1.2 (closed)
Older data (2024)
17 of 17

anomaly detection

Like-for-like groupBest resultModel · precision · stackGradePowerSource · dateRank in group
unknown · b=124.45 inferences/sFC autoencoder (MLPerf Tiny AD)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
Aunknown power n/aMLPerf Tiny v1.2 (closed)
Older data (2024)
16 of 16

keyword spotting

Like-for-like groupBest resultModel · precision · stackGradePowerSource · dateRank in group
unknown · b=12.11 inferences/sDS-CNN (MLPerf Tiny KWS)
not stated · Bosch Hardware-Aware Lowering Engine (HALE) version 1.0.175
Aunknown power n/aMLPerf Tiny v1.2 (closed)
Older data (2024)
17 of 17
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.