timm/resnet50x4_clip_gap.openai

int8_embedl_tensorrt

timm/resnet50x4_clip_gap.openai
INT8
L4

Labels

Image

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.3.0.99 with Embedl optimizations

Input size

288×288

resnet50x4_clip_gap.openai is an image encoder from timm: it turns an image into a 2,560-dimensional embedding, for search, retrieval and as features for other models.

Files

Image	Size
Model docker.io/embedl/model-artifacts:resnet50x4_clip_gap.openai-timm_int8_embedl_tensorrt_l4.c7fd9cf4c7bc17d1	0.50 GiB
Runtime docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0	0.52 GiB