EdgeNeXt-S (timm/edgenext_small.usi_in1k, MIT) at 320px, quantized to INT8 with Kenosis — 128-image calibration, no retraining. 81.53% top-1 from a 7.2 MB single file, on ONNX Runtime or OpenVINO, CPU or GPU, no accelerator required.

Accuracy

ImageNet-1K validation, 49,872 images (disjoint from the 128 calibration images).

model	top-1	Δ vs FP32	size
FP32 baseline	81.565%	—	22.5 MB
Kenosis quantized	81.535%	−0.030	7.16 MB

Run

python

from huggingface_hub import hf_hub_download
import numpy as np, onnxruntime as ort
from PIL import Image
path = hf_hub_download("CoreEpoch/edgenext-small-int8-imagenet", "edgenext_s_320_int8_kenosis.onnx")
sess = ort.InferenceSession(path, providers=["CPUExecutionProvider"])
img = Image.open("your_image.jpg").convert("RGB")
scale = 320 / min(img.size)  # shorter side to 320, center crop — the measured transform
img = img.resize((round(img.width*scale), round(img.height*scale)), Image.BICUBIC)
l, t = (img.width-320)//2, (img.height-320)//2
img = img.crop((l, t, l+320, t+320))
x = (np.asarray(img, np.float32)/255.0 - [0.485,0.456,0.406]) / [0.229,0.224,0.225]
logits = sess.run(None, {"input": x.transpose(2,0,1)[None].astype(np.float32)})[0]
print(int(np.argmax(logits)))

Input 1x3x320x320, RGB, /255, ImageNet mean/std. Output logits [1,1000], sorted-synset order. run_classify.py / eval_imagenet.py reproduce the demo and table.

Integrity & license

edgenext_s_320_int8_kenosis.onnx (7,160,419 B) — SHA-256 D1538E0F392836832E7BBC0C80285396491444B2614E07BC04EE26D38DE7B88C. MIT (base EdgeNeXt, Maaz et al. 2022, retained). Quantized with Kenosis (patent pending) · coreepoch.dev