vit-base-patch16-224 vs vit_small_patch16_224.augreg_in21k_ft_in1k
Specs, VRAM requirements and download trends — updated 6 August 2026.
timm · B
Params
20 M
Context
—
30d
301 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | vit-base-patch16-224 | vit_small_patch16_224.augreg_in21k_ft_in1k |
|---|---|---|
| Parameters | 90 M | 20 M |
| Architecture | ViTForImageClassification | — |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,662,041 | 300,704 |
| Downloads all time | 172.9 M | 8.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-12-22 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
4.7 M301 K
vit-base-patch16-224
vit_small_patch16_224.augreg_in21k_ft_in1k
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
vit_small_patch16_224.augreg_in21k_ft_in1k · fp16
0.6 GB / 24 GB
vit-base-patch16-224 · fp16
0.9 GB / 24 GB
Adjacent comparisons
mobilenetv3_small_100.lamb_in1k vs vit-base-patch16-224
nsfw_image_detection vs vit-base-patch16-224
vit-base-patch16-224 vs fairface_age_image_detection
vit-base-patch16-224 vs mit-b2
vit-base-patch16-224 vs gender-classification
mobilenetv3_small_100.lamb_in1k vs vit_small_patch16_224.augreg_in21k_ft_in1k