Skip to content
Search models or paste a model link. Press Enter to search.

ViT Medium-D/16 (384, reg4, GAP)

timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k
int8_embedl_tensorrt
timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k architecture graph

Select hardware to start

Its measured speed and accuracy, its files and how to run it are per device.

timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k architecture graph
  • timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k
  • INT8
  • L4
Labels
  • Image
  • Classification
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 11.3.0.99 with Embedl optimizations
Input size
384×384

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k is an image classifier from timm. It labels an image with one of the 1,000 ImageNet classes.

Files

Image Size

Model

docker.io/embedl/model-artifacts:vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k-timm_int8_embedl_tensorrt_l4.a1333ab956414763

0.74 GiB

Runtime

docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0

0.52 GiB