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

FocalNet Huge (fl4)

timm/focalnet_huge_fl4.ms_in22k
int8_embedl_tensorrt
timm focalnet_huge_fl4.ms_in22k architecture graph

Select hardware to start

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

timm focalnet_huge_fl4.ms_in22k architecture graph
  • timm/focalnet_huge_fl4.ms_in22k
  • INT8
  • L4
Labels
  • Image
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 11.3.0.99 with Embedl optimizations
Input size
224×224

focalnet_huge_fl4.ms_in22k is an image encoder from timm: it turns an image into a 2,816-dimensional embedding, for search, retrieval and as features for other models.

Files

Image Size

Model

docker.io/embedl/model-artifacts:focalnet_huge_fl4.ms_in22k-timm_int8_embedl_tensorrt_l4.e86bbb8caba3f84d

5.15 GiB

Runtime

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

0.52 GiB