timm/convnext_large.dinov3_lvd1689m

int8_embedl_tensorrt

timm/convnext_large.dinov3_lvd1689m
INT8
L4

Labels

Image

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.3.0.99 with Embedl optimizations

Input size

224×224

convnext_large.dinov3_lvd1689m is an image encoder from timm: it turns an image into a 1,536-dimensional embedding, for search, retrieval and as features for other models.

Files

Image	Size
Model docker.io/embedl/model-artifacts:convnext_large.dinov3_lvd1689m-timm_int8_embedl_tensorrt_l4.240c450f7a435d09	2.22 GiB
Runtime docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0	0.52 GiB