Skip to content
Log in

timm/vit_huge_plus_patch16_dinov3.lvd1689m

int8_embedl_tensorrt
timm vit_huge_plus_patch16_dinov3.lvd1689m architecture graph
timm vit_huge_plus_patch16_dinov3.lvd1689m architecture graph
  • timm/vit_huge_plus_patch16_dinov3.lvd1689m
  • INT8
  • L4
Labels
  • Image
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 11.3.0.99 with Embedl optimizations
Input size
256×256

vit_huge_plus_patch16_dinov3.lvd1689m is an image encoder from timm: it turns an image into a 1,280-dimensional embedding, for search, retrieval and as features for other models.

Files

Image Size

Model

docker.io/embedl/model-artifacts:vit_huge_plus_patch16_dinov3.lvd1689m-timm_int8_embedl_tensorrt_l4.af07de46ac1e0566

 9.96 GiB

Runtime

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

 0.52 GiB