vit-base-patch16-224
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository. However, the weights were converted from the t...
Params
90 M
Context
—
Downloads 30d
15.0 M
Likes
1,050
Download history
daily snapshots · 106 days
▲ 2.7 M in the last 30 days (21.6%)
16.2 M12.5 M
Oct 12Oct 22Nov 1Nov 10
16.2 M4.4 M
Aug 13Sep 12Oct 12Nov 10
16.2 M4.3 M
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 | 0.3 GB | 0.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- ViTForImageClassification
- Parameters
- 90 M
- Tensor type
- F32
- Layers / heads
- 12 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- imagenet-1k, imagenet-21k
- Added to our catalog
- 2026-07-28
Compare with any image-classification model
Popular comparisons
Appears in