Skip to content
Log in

google/vit-base-patch16-224

Embedl-optimized
ViT-B-16 architecture graph
ViT-B-16 architecture graph
  • google/vit-base-patch16-224
  • FP8
  • AGX Thor
Labels
  • Image
  • Classification
Build
Embedl-optimized
Precision
FP8
Runtime
TensorRT 10.13.3.9 with Embedl optimizations
Input size
224×224
Run ViT-B/16 on AGX Thor

ViT-B/16 is Google's Vision Transformer for image classification: it labels an image with one of the 1,000 ImageNet classes.

Methodology

  • Latency: trtexec on the NVIDIA Jetson AGX Thor with TensorRT 10.13.3.9: batch 1, CUDA graphs, median GPU compute time (no copies to and from the GPU).
  • Accuracy: the ImageNette validation split, 3,925 images with ImageNet-1k labels, on both engines.
  • Size: the serialized TensorRT engine.
  • Baseline TensorRT: the original model in FP16 on upstream TensorRT 10.13.3.9, same settings, same device.
  • Build: Embedl Deploy fusion and quantization, calibrated on 128 ImageNette training images, exported to ONNX and compiled with trtexec.