Depth Anything V2 Small INT8

Mobile CPUvivo X300SME2

This is an INT8-quantized version of Depth Anything V2 Small optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was quantized using PT2E static symmetric per-channel quantization and exported to the .pte format for efficient monocular depth estimation on ARM Cortex-A processors (AWS Graviton, mobile ARM, embedded).View on Hugging Face

Accuracyvs base model

AbsRel0.06↑0.01

RMSE0.35 m↑0.04 m

δ1 < 1.2596.35%

About this version

Original Model:: Depth-Anything-V2-Small-hf by Not specified — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

This repository contains a converted or optimized version of the Original Model (the “Optimized Model”). The Original Model has been converted or optimized as described above for execution on Arm-based platforms.

No retraining or fine-tuning of the Original Model was performed as part of the conversion or optimization. The conversion or optimization was not intended to change the Original Model’s behavior or intended use.

Original Model and Documentation

For information about the Original Model, including its development, training data, intended uses, limitations and other relevant information, please refer to the Original Model repository. Information in that repository was provided by the original developer or other third parties and, unless expressly stated otherwise, has not been independently verified by Arm.

Licenses and Third-Party Terms

Use of the Original Model and the Optimized Model is subject to the applicable licenses, usage restrictions and other terms identified above and in the relevant repositories. Publication of the Optimized Model does not grant any rights beyond those provided under the applicable license terms.

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

About this version

Original Model:: Depth-Anything-V2-Small-hf by Not specified — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

Original Model and Documentation

Licenses and Third-Party Terms

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Metric	Resultsvs baseline	Change
End to end latency p50	727.73ms1336.61ms	−608.89 ms
End to end latency p90	735.64ms1344.71ms	−609.07 ms
End to end latency p99	737.49ms1350.50ms	−613.01 ms
Peak memory	380.10MB439.43MB	−59.33 MB
Time to first inference	750.39ms1122.84ms	−372.45 ms
Frames per second	1.37fps0.80fps	+0.57 fps
AbsRel	0.060.05	+0.01
RMSE	0.35m0.31m	+0.04 m
δ1 < 1.25	96.35%97.32%	−0.97%

Dataset	nyu_depth_v2	nyu_depth_v2
Sample count	654	654
Batch size	1	1
Input resolution	518x686	518x686
Runs	50	50
Warmup runs	10	10

Depth Anything V2 Small INT8

Depth Anything V2 Small INT8

Model Evaluation

Configuration

Comparability

Purpose of this Release