Next Generation Snapdragon Mobile Platform MTP: edge AI benchmarks
Key results
| Workload | Best result | Model · precision | Power · perf/W | Grade · date | Source |
|---|---|---|---|---|---|
| tiny image classification | 10437 inferences/s batch 1 | ResNet-8 (MLPerf Tiny IC) PTQ · Qualcomm AI Stack | unknown | A 2025-09-17 (published) | MLPerf Tiny v1.3 (closed) |
| visual wake words | 8753 inferences/s batch 1 | MobileNetV1 0.25 (MLPerf Tiny VWW) PTQ · Qualcomm AI Stack | unknown | A 2025-09-17 (published) | MLPerf Tiny v1.3 (closed) |
| anomaly detection | 14625 inferences/s batch 1 | FC autoencoder (MLPerf Tiny AD) PTQ · Qualcomm AI Stack | unknown | A 2025-09-17 (published) | MLPerf Tiny v1.3 (closed) |
| keyword spotting | 15396 inferences/s batch 1 | DS-CNN (MLPerf Tiny KWS) PTQ · Qualcomm AI Stack | unknown | A 2025-09-17 (published) | MLPerf Tiny v1.3 (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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 Next Generation Snapdragon Mobile Platform MTP 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 group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| mid-size CNN · b=1 | 10437 inferences/s | ResNet-8 (MLPerf Tiny IC) PTQ · Qualcomm AI Stack | A | unknown power n/a | MLPerf Tiny v1.3 (closed) 2025-09-17 (published) | 1 of 19 |
visual wake words
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| mobile-class CNN · b=1 | 8753 inferences/s | MobileNetV1 0.25 (MLPerf Tiny VWW) PTQ · Qualcomm AI Stack | A | unknown power n/a | MLPerf Tiny v1.3 (closed) 2025-09-17 (published) | 1 of 17 |
anomaly detection
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| unknown · b=1 | 14625 inferences/s | FC autoencoder (MLPerf Tiny AD) PTQ · Qualcomm AI Stack | A | unknown power n/a | MLPerf Tiny v1.3 (closed) 2025-09-17 (published) | 1 of 16 |
keyword spotting
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| unknown · b=1 | 15396 inferences/s | DS-CNN (MLPerf Tiny KWS) PTQ · Qualcomm AI Stack | A | unknown power n/a | MLPerf Tiny v1.3 (closed) 2025-09-17 (published) | 1 of 17 |
How to read these numbers
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.