ANEForge: Python for direct computation on the Apple Neural Engine
Paper • 2606.17090 • Published • 1
An unmodified duplicate of google/vit-base-patch16-224, tagged for use with
ANEForge so the weights load and run directly on the
Apple Neural Engine (no CoreML). Weights are byte-identical to the source; see the original repo for
the model details. Licensed apache-2.0 from the source.
import aneforge as af
vit = af.load_vit("aneforge/vit-base-patch16-224")
print(vit.classify(image)) # top-k (label, logit)
ANEForge compiles the model's graph into a single ANE program and streams the weights from this repo
via huggingface_hub. See the docs and the
paper.
Base model
google/vit-base-patch16-224