Skip to content
Search models or paste a model link. Press Enter to search.

DeiT Base/16 (384)

timm/deit_base_patch16_384.fb_in1k
Left and right arrow keys switch the vendor.
int8_embedl_tensorrt
timm deit_base_patch16_384.fb_in1k architecture graph
timm deit_base_patch16_384.fb_in1k architecture graph
  • timm/deit_base_patch16_384.fb_in1k
  • INT8
  • AGX Thor
Labels
  • Image
  • Classification
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 10.16.2.10 with Embedl optimizations
Input size
384×384

deit_base_patch16_384.fb_in1k is an image classifier from timm. It labels an image with one of the 1,000 ImageNet classes.

License: apache-2.0 (the upstream model's).

Files

Image Size

Model

docker.io/embedl/model-artifacts:deit_base_patch16_384.fb_in1k-timm_int8_embedl_tensorrt_thor.bff09fff9530b8b5

—

Runtime

docker.io/embedl/models:runtimes.tensorrt.arm64.2026101815014ee0

—

Select hardware to start

Its measured speed and accuracy, its files and how to run it are per device.

Model variants (Pareto)

4 Embedl builds of DeiT Base/16 (384) on 4 devices: latency against Top-1. Click a build to open it.

82.082.583.083.584.0Top-1 (%)024681012Latency (ms)↖ Better