timm/vit_base_patch16_clip_224.openai

int8_embedl_tensorrt

timm/vit_base_patch16_clip_224.openai
INT8
L4

Labels

Image

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.3.0.99 with Embedl optimizations

Input size

224×224

vit_base_patch16_clip_224.openai is an image encoder from timm: it turns an image into a 512-dimensional embedding, for search, retrieval and as features for other models.

Files

Image	Size
Model docker.io/embedl/model-artifacts:vit_base_patch16_clip_224.openai-timm_int8_embedl_tensorrt_l4.3c2cf6c056a95452	0.77 GiB
Runtime docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0	0.52 GiB