vit_tiny_r_s16_p8_224.augreg_in21k
A ResNet - Vision Transformer (ViT) hybrid image classification model. Trained on ImageNet-21k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman.
Params
10 M
Context
—
Downloads 30d
274 K
Likes
0
Download history
daily snapshots · 106 days
▲ 0 in the last 30 days (0.0%)
274 K274 K
Oct 12Oct 22Nov 1Nov 10
403 K274 K
Aug 13Sep 12Oct 12Nov 10
436 K274 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.0 GB | 0.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 10 M
- Tensor type
- F32
- Licence
- apache-2.0
- First seen on the Hub
- 2022-12-23
- Training datasets
- imagenet-21k
- Added to our catalog
- 2026-07-28
Compare with any image-classification model