Skip to content
Log in

timm/convnext_base.clip_laion2b

int8_embedl_tensorrt
timm convnext_base.clip_laion2b architecture graph
timm convnext_base.clip_laion2b architecture graph
  • timm/convnext_base.clip_laion2b
  • INT8
  • L4
Labels
  • Image
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 11.3.0.99 with Embedl optimizations
Input size
256×256

convnext_base.clip_laion2b is an image encoder from timm: it turns an image into a 640-dimensional embedding, for search, retrieval and as features for other models.

Files

Image Size

Model

docker.io/embedl/model-artifacts:convnext_base.clip_laion2b-timm_int8_embedl_tensorrt_l4.fd240a0e7a9fb97f

 1.00 GiB

Runtime

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

 0.52 GiB