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

ConvNeXt Zepto (rms, ols)

timm/convnext_zepto_rms_ols.ra4_e3600_r224_in1k
Left and right arrow keys switch the vendor.
int8_embedl_tensorrt
timm convnext_zepto_rms_ols.ra4_e3600_r224_in1k architecture graph
timm convnext_zepto_rms_ols.ra4_e3600_r224_in1k architecture graph
  • timm/convnext_zepto_rms_ols.ra4_e3600_r224_in1k
  • INT8
  • AGX Thor
Labels
  • Image
  • Classification
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 10.16.2.10 with Embedl optimizations
Input size
224×224

convnext_zepto_rms_ols.ra4_e3600_r224_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:convnext_zepto_rms_ols.ra4_e3600_r224_in1k-timm_int8_embedl_tensorrt_thor.ece655afc77e98a1

—

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 ConvNeXt Zepto (rms, ols) on 4 devices: latency against Top-1. Click a build to open it.

71.071.572.072.573.0Top-1 (%)0.00.51.01.52.02.53.0Latency (ms)↖ Better