Skip to content
Log in

timm/beit3_base_patch16_224.indomain_pt

int8_embedl_tensorrt
timm beit3_base_patch16_224.indomain_pt architecture graph
timm beit3_base_patch16_224.indomain_pt architecture graph
  • timm/beit3_base_patch16_224.indomain_pt
  • INT8
  • L4
Labels
  • Image
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 11.3.0.99 with Embedl optimizations
Input size
224×224

beit3_base_patch16_224.indomain_pt 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:beit3_base_patch16_224.indomain_pt-timm_int8_embedl_tensorrt_l4.aa0c4d9d06c45a5a

 0.86 GiB

Runtime

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

 0.52 GiB