DINOv2-ViT-S14-OpenVINO

DINOv2-ViT-S14 for Intel NPUs, GPUs and CPUs: dinov2_s_fp16 from litert-community/DINOv2-ViT-S14-LiteRT as ONNX (tf2onnx 1.17.0, opset 17), OpenVINO IR with fp32 weights, and a precompiled Intel NPU blob. On the NPU of a Core Ultra 9 386H the blob runs in 27.55 ms per run, numpy input to numpy output.

Scripts, raw records, and the same table for all 52 graphs of LiteRT-Models: https://github.com/john-rocky/windows-zoo

Files

file	bytes	sha256
`dinov2_s_fp16.onnx`	87,855,002	`8f36d01fe1635da9d09b4958e17a9b43c8b25438a4422e59cab1f4414d506625`
`openvino/dinov2_s_fp16.xml`	769,315	`3e8808634ef2173de6c1addd9762f959433b070eb0966c018230e8feddf626a6`
`openvino/dinov2_s_fp16.bin`	87,658,556	`294d224b5c1f074ff3e08b027bfe9011452d158bb2b25e6eef65980c07809fed`
`npu/dinov2_s_fp16.blob`	54,415,489	`dc8b1157d21d528bc89041b7ec59287b98cacd17a1f67e878a9b70299ff52106`

The NPU blob was compiled with OpenVINO 2026.4.1, Intel NPU driver 32.0.100.4841 (OpenVINO reports NPU_DRIVER_VERSION 1004841, NPU_COMPILER_VERSION 524292). If import_model refuses a blob on another driver or OpenVINO version, compile the IR instead (the commented line in the snippet).

How it was measured

MSI Stealth 16 AI+ (Core Ultra 9 386H, RTX 5080 Laptop GPU at a 95 W power limit, Windows 11 build 26200.9711, on AC power), 2026-11-07. On the laptop, each row is one process: load, one run, 5 warmup runs, then the median of 30 timed runs (2 warmup + 10 timed runs when the first run takes more than 3 s), numpy input to numpy output, every runtime at its default settings, one process at a time, each started after the CPU, the RTX and the Intel GPU had gone idle (the thresholds are in METHOD.md of the GitHub repo). Output check: each output against the CPU output in fp32 on the same input (ONNX Runtime's CPU EP); PASS = cosine ≥ 0.99, no NaN or Inf, and top-1 agreement ≥ 0.99 for class scores. The Snapdragon rows are Qualcomm AI Hub profile jobs of the same ONNX files (their own timer).

Speed and output check

processor	runtime	file	ms	load s	output check
Intel AI Boost NPU	OpenVINO 2026.4.1	`npu/` blob (`import_model`)	27.55	0.04	FAIL: output_0_output: cos 0.0365 < 0.99
Intel AI Boost NPU	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	`.onnx`, compiled when the session loads	27.43	35.58	FAIL: output_0_output: cos 0.0364 < 0.99
Intel Graphics (iGPU)	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	`.onnx`	48.20	1.77	PASS (cos ≥ 0.9999)
RTX 5080 Laptop (95 W limit)	ONNX Runtime 1.31.1, CUDA EP	fp16 copy of the `.onnx` (not in this repo)	8.95	1.23	PASS (cos ≥ 0.9963)
RTX 5080 Laptop (95 W limit)	ONNX Runtime 1.31.1, CUDA EP	`.onnx`	11.08	1.22	PASS (cos ≥ 0.9999)
Core Ultra 9 386H CPU	ONNX Runtime 1.31.1, CPU EP	`.onnx`	139.66	0.21	reference
Snapdragon X2 Elite NPU	Qualcomm AI Hub, precompiled QNN ONNX	`.onnx` compiled by AI Hub	56.22	0.43	not compared (AI Hub profile job, 2026-10-30)
Snapdragon X2 Elite NPU	Qualcomm AI Hub, ONNX Runtime QNN EP	`.onnx`, compiled when it loads	64.31	64.43	not compared (AI Hub profile job, 2026-10-30)
Galaxy S26 NPU	Qualcomm AI Hub, precompiled QNN ONNX	`.onnx` compiled by AI Hub	60.03	0.25	not compared (AI Hub profile job, 2026-10-30)

The ONNX file against the source .tflite (LiteRT interpreter on the CPU, the same input): PASS, cosine ≥ 0.9999 for every output.

Run it on the Intel NPU

Download this repo, then run the snippets from its folder:

pip install huggingface_hub
hf download mlboydaisuke/DINOv2-ViT-S14-OpenVINO --local-dir DINOv2-ViT-S14-OpenVINO
cd DINOv2-ViT-S14-OpenVINO

OpenVINO (pip install openvino==2026.4.1):

import numpy as np
import openvino as ov

core = ov.Core()
if "NPU" not in core.available_devices:
    raise SystemExit(f"no Intel NPU visible to OpenVINO: {core.available_devices}")
with open("npu/dinov2_s_fp16.blob", "rb") as f:
    compiled = core.import_model(f.read(), "NPU")  # precompiled: no compile at load
# or compile the IR on this machine: compiled = core.compile_model("openvino/dinov2_s_fp16.xml", "NPU")
# replace the zeros with your preprocessed input (float32, the shapes printed by compiled.inputs)
feeds = {i.get_any_name(): np.zeros(list(i.shape), np.float32) for i in compiled.inputs}
outputs = compiled(feeds)
print({o.get_any_name(): outputs[o].shape for o in compiled.outputs})

ONNX Runtime with the OpenVINO EP (pip install onnxruntime==1.31.1 onnxruntime-ep-openvino==1.8.1):

import numpy as np
import onnxruntime as ort
import onnxruntime_ep_openvino as ov_ep

ort.register_execution_provider_library(ov_ep.get_ep_name(), ov_ep.get_library_path())
npu = [d for d in ort.get_ep_devices()
       if d.ep_name == ov_ep.get_ep_name() and d.ep_metadata.get("ov_device") == "NPU"]
if not npu:
    raise SystemExit("no Intel NPU visible to the OpenVINO EP")
so = ort.SessionOptions()
so.add_provider_for_devices(npu, {})
sess = ort.InferenceSession("dinov2_s_fp16.onnx", sess_options=so)  # compiles for the NPU here
# replace the zeros with your preprocessed input (float32)
feeds = {i.name: np.zeros(i.shape, np.float32) for i in sess.get_inputs()}
outputs = sess.run(None, feeds)
print([o.shape for o in outputs])