vit_tiny_patch16_224.augreg_in21k
A Vision Transformer (ViT) 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
207 K
Likes
5
Download history
daily snapshots · 74 days
▲ 0 in the last 30 days (0.0%)
207 K207 K
Oct 12Oct 22Nov 1Nov 10
218 K207 K
Aug 29Sep 22Oct 17Nov 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
- 2022-12-22
- Training datasets
- imagenet-21k
- Added to our catalog
- 2026-08-29
Compare with any image-classification model