timm/davit_huge_fl.msft_florence2

int8_embedl_tensorrt

timm/davit_huge_fl.msft_florence2
INT8
L4

Labels

Image

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.3.0.99 with Embedl optimizations

Input size

768×768

davit_huge_fl.msft_florence2 is an image encoder from timm: it turns an image into a 2,048-dimensional embedding, for search, retrieval and as features for other models.

Files

Image	Size
Model docker.io/embedl/model-artifacts:davit_huge_fl.msft_florence2-timm_int8_embedl_tensorrt_l4.6b243853a95a0b96	3.15 GiB
Runtime docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0	0.52 GiB