timm / image-classification Open weights updated 1 year ago

convnextv2_large.fcmae_ft_in22k_in1k_384

Name: convnextv2_large.fcmae_ft_in22k_in1k_384
Author: timm

A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k.

Params

200 M

Context

—

Downloads 30d

327 K

Likes

Commercial use: not allowed · cc-by-nc-4.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 56 days

▲ 41 K in the last 30 days (14.3%)

327 K197 K

Sep 16Oct 4Oct 23Nov 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	0.8 GB	1.4 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: 200 M
Tensor type: F32
Licence: cc-by-nc-4.0
First seen on the Hub: 2023-01-05
Training datasets: imagenet-1k, imagenet-1k
Added to our catalog: 2026-09-16

Compare with any image-classification model

Popular comparisons

vit-base-patch16-224 15.0 M Gender-Classifier-Mini 8.1 M nsfw_image_detection 1.6 M gender-classification 1.3 M efficientvit_l2.r288_in1k 1.3 M swinv2-tiny-patch4-window16-256 390 K