timm/mvitv2_huge_cls.fb_inw21k

int8_embedl_tensorrt

timm/mvitv2_huge_cls.fb_inw21k
INT8
L4

Labels

Image

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.3.0.99 with Embedl optimizations

Input size

224×224

mvitv2_huge_cls.fb_inw21k is an image encoder from timm: it turns an image into a 1,536-dimensional embedding, for search, retrieval and as features for other models.

Files

Image	Size
Model docker.io/embedl/model-artifacts:mvitv2_huge_cls.fb_inw21k-timm_int8_embedl_tensorrt_l4.6335675c5822c78e	7.47 GiB
Runtime docker.io/embedl/models:runtimes.tensorrt.amd64.2026101815014ee0	0.52 GiB