Downloads · 30 days
6
15% of all-time downloads
gcvit_xxtiny
litert-community/gcvit_xxtiny
gcvit_xxtiny is a image classification model from litert-community. Use it when you need a label for an image. It is set up for litert.
Converted TIMM image classification model for LiteRT.
All-time downloads
41
Public
Repo size
55.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tflite55.8 MB · 100%
At a glance
- Task
- Image Classification
- Library
- litert
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 12, 2026
- SHA
- e3e27d8c
Datasets
Model card
From the Hugging Face model README
gcvit_xxtiny
Converted TIMM image classification model for LiteRT.
- Source architecture:
gcvit_xxtiny - Source checkpoint:
https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights-morevit/gcvit_xxtiny_224_nvidia-d1d86009.pth - File:
model.tflite - Input:
float32tensor in NCHW layout, shape[1, 3, 224, 224] - Output: ImageNet-1K logits, shape
[1, 1000]
Runtime Status
- CPU smoke test: passed with LiteRT
CompiledModel. - GPU delegation: currently blocked for this model by rank-5 tensor patterns in the GPU backend, mostly
RESHAPE,TRANSPOSE, and related window/attention operations. The model is published as CPU-ready while GPU support is being improved.
- Task
- Image Classification
- Library
- litert
- Created
- May 12, 2026
- Updated
- May 12, 2026