depth-anything-v2-small-int8-ov

OpenVINO IR export of depth-anything/Depth-Anything-V2-Small-hf, quantized to INT8 — 26 MB.


Quantization	weight compression (NNCF)
Lesson	04 Depth Anything V2
Built by	`convert/convert_all.py` of the ARCademy OpenVINO courseware

Dynamic H/W, both multiples of 14 (518 default). Larger value = closer.

from huggingface_hub import snapshot_download
model_dir = snapshot_download("circulus/depth-anything-v2-small-int8-ov")

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for circulus/depth-anything-v2-small-int8-ov

Base model

Finetuned

(4)

this model