Downloads · 30 days
20
24% of all-time downloads
Synaptics/yolov8-od-nano-jellyfish-int8-torq
yolov8-od-nano-jellyfish-int8-torq is a machine learning model from Synaptics. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for torq. The card lists the license as agpl-3.0.
This repository provides model files for a Jellyfish object detection model based on Yolo V8 nano. It is ready to run on the Synaptics SL2610-series Torq with Coral NPU.
Downloads · 30 days
20
24% of all-time downloads
All-time downloads
85
Public
Repo size
13.4 MB
Likes
0
Public
Click a slice to open those files.
.pt6.3 MB · 47%
From the Hugging Face model README
This repository provides model files for a Jellyfish object detection model based on Yolo V8 nano. It is ready to run on the Synaptics SL2610-series Torq with Coral NPU.
The model was originally created for the Jellectronica Demonstration at Google IO 2026. It was trained with permission on video from the Monterey Bay Aquarium.
It was exported from Ultralytics to TFlite with INT8 quantization, then compiled to run on the Torq NPU.
| Platform | Model | Environment | NPU Clock | Inferernce Time |
|---|---|---|---|---|
| SL2619 2GB | moon320 | Torq v2.0.0 | 1 GHz | 36 ms |