Sponsored by
Crazyrouter
-The enterprise-grade, cost-effective AI API gateway that provides one API key to access 300+ AI models through OpenAI-compatible endpoints, with
Introduction of efficientvit-int8-xnnpack-executorch-raspberrypi5
Model Details of efficientvit-int8-xnnpack-executorch-raspberrypi5
EfficientViT optimized for Arm-based Edge Linux
EfficientViT image classification model, optimized with INT8 quantization and exported as an ExecuTorch program for the XNNPACK CPU backend on Arm-based platforms.
This repository contains an optimized version of EfficientViT for image classification. The model is provided as an ExecuTorch
.pte
file using the XNNPACK with KleidiAI delegate, targeting Edge Linux systems. Precision: INT8 weights (quantization details not recorded in metadata).
Key results
Area
Result
Model format
ExecuTorch (.pte)
Target device class
Edge Linux
Reference device
Raspberry Pi 5 (16GB) (Cortex-A76, 4 cores)
Primary performance result
1.24x lower p50 latency (26.01 ms to 20.90 ms)
Accuracy result
Top-1 accuracy 78.68% (-0.68 pp vs. baseline)
Size / memory result
2.06x smaller model (37.39 MB to 18.12 MB), 31.69 MB peak memory
Performance was measured on the reference configuration below. Results do not guarantee identical performance on every Arm-based system.
Reference configuration
Field
Value
Device / platform
Raspberry Pi 5 (16GB)
CPU / accelerator
Cortex-A76, 4 cores, 2.4 GHz
OS
Raspberry Pi OS Bookworm
Runtime
ExecuTorch 1.1.0
Backend / delegate
XNNPACK with KleidiAI, 4 threads
Batch size
1
Input resolution
224x224
Precision
INT8 weights (quantization details not recorded in metadata)
Runs
200 measured, 20 warm-up
Performance results
Metric
Original / baseline
Optimized
Improvement
p50 end-to-end latency
26.01 ms
20.90 ms
1.24x
Peak memory
50.92 MB
31.69 MB
1.61x less
Model size
37.39 MB
18.12 MB
2.06x smaller
Accuracy
Evaluation setup
Field
Value
Dataset
ImageNet-1k
Split
val
Number of samples
5,000
Evaluation runtime
ExecuTorch
Accuracy results
Metric
Original / baseline
Optimized
Change
Top-1 accuracy
79.36%
78.68%
-0.68 pp
Top-5 accuracy
-
94.34%
-
Users should re-evaluate the model on their own data before production use.
Optimization approach
Optimization area
Applied?
Notes
Model conversion
Yes
PyTorch model exported to ExecuTorch (.pte)
Quantization
Yes
INT8 weights (quantization details not recorded in metadata)
Runtime/backend selection
Yes
XNNPACK with KleidiAI, 4 threads
Accuracy validation
Yes
ImageNet-1k, 5000 samples
Performance validation
Yes
Measured on Raspberry Pi 5 (16GB)
Intended use
This model is intended for developers evaluating image classification workloads on Arm-based Edge Linux platforms. It is suitable as a reference implementation for benchmarking, prototyping, and integration exploration.
Limitations
Performance depends on the target device, runtime version, backend support, memory configuration, and system load.
Accuracy was measured on a 5,000-image subset of the ImageNet-1k validation set, not the full 50,000 images.
This repository is not a replacement for the original model documentation.
About this version
Original Model:
EfficientViT by MIT HAN Lab -
Repository
Optimization/conversion:
INT8 quantization and ExecuTorch
.pte
export with XNNPACK + KleidiAI backend support for execution on Arm-based platforms.
Converted/optimized by:
Nota AI, using Arm AI Model Optimizer
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.
Purpose of this Release
The Optimized Model is provided as a reference implementation to demonstrate and evaluate execution and performance on Arm-based systems. It is not a production-ready or supported solution.
Arm's publication of the Optimized Model does not constitute an endorsement or certification of the Original Model or a representation that the Optimized Model is suitable for production use or any particular purpose.
To the fullest extent permitted by applicable law (i) the Optimized Model is provided "as is." Arm makes no representations or warranties that the Original Model, the Optimized Model or their outputs are accurate, safe, secure, non-infringing, legally compliant, suitable for production use or fit for any particular purpose; and (ii) Arm will not be liable for any loss or damage arising from or in connection with the Optimized Model, its use or its outputs.
You are responsible for independently evaluating the Optimized Model, its outputs and its suitability for your intended use, including compliance with applicable legal, regulatory, safety and security requirements.
Arm does not commit to provide ongoing support, maintenance or updates for the Optimized Model. Any use of or reliance on the Optimized Model or its outputs is at your own risk.
Runs of Arm efficientvit-int8-xnnpack-executorch-raspberrypi5 on huggingface.co
32
Total runs
0
24-hour runs
0
3-day runs
3
7-day runs
3
30-day runs
More Information About efficientvit-int8-xnnpack-executorch-raspberrypi5 huggingface.co Model
More efficientvit-int8-xnnpack-executorch-raspberrypi5 license Visit here:
efficientvit-int8-xnnpack-executorch-raspberrypi5 huggingface.co is an AI model on huggingface.co that provides efficientvit-int8-xnnpack-executorch-raspberrypi5's model effect (), which can be used instantly with this Arm efficientvit-int8-xnnpack-executorch-raspberrypi5 model. huggingface.co supports a free trial of the efficientvit-int8-xnnpack-executorch-raspberrypi5 model, and also provides paid use of the efficientvit-int8-xnnpack-executorch-raspberrypi5. Support call efficientvit-int8-xnnpack-executorch-raspberrypi5 model through api, including Node.js, Python, http.
Arm efficientvit-int8-xnnpack-executorch-raspberrypi5 online free
efficientvit-int8-xnnpack-executorch-raspberrypi5 huggingface.co is an online trial and call api platform, which integrates efficientvit-int8-xnnpack-executorch-raspberrypi5's modeling effects, including api services, and provides a free online trial of efficientvit-int8-xnnpack-executorch-raspberrypi5, you can try efficientvit-int8-xnnpack-executorch-raspberrypi5 online for free by clicking the link below.
Arm efficientvit-int8-xnnpack-executorch-raspberrypi5 online free url in huggingface.co:
efficientvit-int8-xnnpack-executorch-raspberrypi5 is an open source model from GitHub that offers a free installation service, and any user can find efficientvit-int8-xnnpack-executorch-raspberrypi5 on GitHub to install. At the same time, huggingface.co provides the effect of efficientvit-int8-xnnpack-executorch-raspberrypi5 install, users can directly use efficientvit-int8-xnnpack-executorch-raspberrypi5 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
efficientvit-int8-xnnpack-executorch-raspberrypi5 install url in huggingface.co: