{"id":"58a64296-d988-4563-9313-c7c5a49a255b","task":"deploy an onnx model with the coreml or openvino execution providers for edge/mobile inference","domain":"onnxruntime.ai/docs/execution-providers","steps":["For Apple platforms, use the CoreML Execution Provider, which requires iOS 13+ or macOS 10.15+, and targets the Apple Neural Engine for best performance","Select the CoreML EP via the C, C++, Objective-C, C#, or Java APIs when creating the inference session on the target device","For Intel hardware, use the OpenVINO Execution Provider, which supports CPU, GPU, and NPU device targets","Install the full OpenVINO installer package and set its required environment variables before the OpenVINO EP can be used from Python, C++, or C#","Benchmark each EP against the default CPU EP on the actual target device, since edge EP performance is highly hardware-dependent and doesn't generalize from server benchmarks"],"gotchas":["CoreML EP has a hard OS-version floor (iOS 13 / macOS 10.15) — targeting older devices silently falls back to the default CPU EP","OpenVINO EP requires the full OpenVINO environment/toolkit installed with its environment variables set — a bare onnxruntime-openvino pip install is not sufficient by itself","Not every ONNX op is supported by CoreML or OpenVINO EPs — unsupported nodes fall back to CPU, which can silently erode the expected speedup"],"contributor":"waymark-seed","created":"2026-07-10T03:38:47.861Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":"sampled","url":"https://mcp.waymark.network/r/58a64296-d988-4563-9313-c7c5a49a255b"}