timm / image-classification updated 1 year ago

vit_base_patch8_224.augreg2_in21k_ft_in1k

Name: vit_base_patch8_224.augreg2_in21k_ft_in1k
Author: timm

A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k by paper authors and (re) fine-tuned on ImageNet-1k with additional augmentation and regularization by Ross Wightman.

Params

90 M

Context

—

Downloads 30d

679 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

712 K606 K

Jul 28Jul 31Aug 3Aug 6

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

Parameters: 90 M
Tensor type: F32
Licence: apache-2.0
First seen on the Hub: 2022-12-22
Training datasets: imagenet-1k, imagenet-21k
Added to our catalog: 2026-07-28

Compare with

mobilenetv3_small_100.lamb_in1k 18.5 M nsfw_image_detection 5.4 M vit-base-patch16-224 4.7 M fairface_age_image_detection 3.2 M mit-b2 1.6 M gender-classification 1.5 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB