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

ViT Base/16 (DINOv3)

timm/vit_base_patch16_dinov3.lvd1689m
int8_embedl_tensorrt
timm vit_base_patch16_dinov3.lvd1689m architecture graph

Select hardware to start

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

timm vit_base_patch16_dinov3.lvd1689m architecture graph
  • timm/vit_base_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_base_patch16_dinov3.lvd1689m is an image encoder from timm: it turns an image into a 768-dimensional embedding, for search, retrieval and as features for other models.

Files

Image Size

Model

docker.io/embedl/model-artifacts:vit_base_patch16_dinov3.lvd1689m-timm_int8_embedl_tensorrt_l4.17d64d7832642e28

0.96 GiB

Runtime

docker.io/embedl/models:runtimes.tensorrt.amd64.2026102005300fa3

0.52 GiB