Skip to page content
SAVRN
Search Plan a project

Open-weight model

RK3576-SEGMENT-yolov8s-seg

by RKNNAI RKNNAI/RK3576-SEGMENT-yolov8s-seg

RK3576-SEGMENT-yolov8s-seg is an open-weight model from RKNNAI, released under GNU Affero General Public License 3.0. Its published files total 15.9 MB.

This repository provides RKNN deployment configurations of yolov8s-seg for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment.

Parameters—
Context—
Weights15.9 MB
Licenseagpl-3.0
AccessOpen weights
Monthly Downloads—

Model Card

By RKNNAI, published under agpl-3.0, revision 875177876340.

This repository provides RKNN deployment configurations of yolov8s-seg for RK3576. From the directory where you ran the download command, enter the configuration directory and verify: All entries must report OK before deployment. - Supported chips are listed per configuration above. - Use the matching files from the same configuration. The model is provided through RKNN Model Zoo and originates from airockchip/ultralyticsyolov8. The upstream license is GNU AGPL v3; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file. This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration.

Read RKNNAI's full model card

yolov8s-seg

English | 简体中文

1. Model Introduction

This repository provides RKNN deployment configurations of yolov8s-seg for RK3576.

Field Value
Model ID RKNNAI/RK3576-SEGMENT-yolov8s-seg
Display Name RK3576-SEGMENT-yolov8s-seg
Source Model https://github.com/airockchip/ultralytics_yolov8
Model Type SEGMENT

Available Models

Configuration Supported Chips RKNN Runtime Version Quantization NPU Cores Resolution
yolov8s-seg-640x640-w8a8-1 RK3576 v2.4.0 w8a8 1 640x640

2. Files

Path Description
README.md English documentation
README_CN.md Chinese documentation
LICENSE License
yolov8s-seg-640x640-w8a8-1/ Deployment configuration

3. Download

ModelScope

Full repository:

modelscope download --model RKNNAI/RK3576-SEGMENT-yolov8s-seg --revision v2.4.0 --local_dir ./RK3576-SEGMENT-yolov8s-seg

Selected configuration and root documents:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK3576-SEGMENT-yolov8s-seg",
    revision="v2.4.0",
    allow_patterns=["README.md", "README_CN.md", "LICENSE", "yolov8s-seg-640x640-w8a8-1/**"],
    local_dir="./RK3576-SEGMENT-yolov8s-seg",
)

Hugging Face

Full repository:

hf download RKNNAI/RK3576-SEGMENT-yolov8s-seg --revision v2.4.0 --local-dir ./RK3576-SEGMENT-yolov8s-seg

Selected configuration and root documents:

hf download RKNNAI/RK3576-SEGMENT-yolov8s-seg --revision v2.4.0 --local-dir ./RK3576-SEGMENT-yolov8s-seg --include README.md README_CN.md LICENSE 'yolov8s-seg-640x640-w8a8-1/**'

4. SHA-256 Verification

From the directory where you ran the download command, enter the configuration directory and verify:

cd ./RK3576-SEGMENT-yolov8s-seg/yolov8s-seg-640x640-w8a8-1
sha256sum -c SHA256SUMS

All entries must report OK before deployment.

5. Compatibility and Limitations

  • Supported chips are listed per configuration above.
  • Use the matching files from the same configuration.

6. Copyright and License

The model is provided through RKNN Model Zoo and originates from airockchip/ultralytics_yolov8. The upstream license is GNU AGPL v3; see LICENSE. Original copyright and attribution notices are retained in the accompanying license file.

This distribution converts the source model to RKNN format for RK3576, using the precision specified in each configuration.

Identity and Version

Repository
RKNNAI/RK3576-SEGMENT-yolov8s-seg
Publisher
RKNNAI
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
8751778763408f421be1ce56c8d30e79dc516278
First published
2026-10-02
Last updated
2026-10-02

Files and Weights

9 files, 15.9 MB in total.

Configuration1 file · 864 B
Documentation5 files · 43.4 KB
Other2 files · 15.9 MB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
yolov8s-seg-640x640-w8a8-1/config.jsonConfiguration864 B —
LICENSEDocumentation34.5 KB —
README.mdDocumentation2.8 KB —
README_CN.mdDocumentation2.5 KB —
yolov8s-seg-640x640-w8a8-1/README.mdDocumentation1.9 KB —
yolov8s-seg-640x640-w8a8-1/README_CN.mdDocumentation1.8 KB —
yolov8s-seg-640x640-w8a8-1/SHA256SUMSOther316 B —
yolov8s-seg-640x640-w8a8-1/yolov8s-seg.rknnOther15.9 MB 689523a26dde
.gitattributesRepository1.6 KB —

License and Download

License
agpl-3.0
Access
Open weights, no gate
Download from RKNNAI

Released by RKNNAI through its official repository on Hugging Face. Read the license.

Questions About RK3576-SEGMENT-yolov8s-seg

Can I use RK3576-SEGMENT-yolov8s-seg commercially?

Yes, with conditions. RK3576-SEGMENT-yolov8s-seg is released under GNU Affero General Public License 3.0. The AGPL 3.0 is a strong copyleft license. Commercial use is allowed, but a modified version made available to users over a network must be released with its source code under the same license.