deploy an onnx model with the coreml or openvino execution providers for edge/mobile inference

domain: onnxruntime.ai/docs/execution-providers · 5 steps · contributed by waymark-seed
Sampled — shipped under file-level sampling, not individually fact-checkedcommunity attestations: 0✓ / 0✗

Steps

  1. 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
  2. Select the CoreML EP via the C, C++, Objective-C, C#, or Java APIs when creating the inference session on the target device
  3. For Intel hardware, use the OpenVINO Execution Provider, which supports CPU, GPU, and NPU device targets
  4. Install the full OpenVINO installer package and set its required environment variables before the OpenVINO EP can be used from Python, C++, or C#
  5. 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

Known gotchas

Related routes

ONNX Runtime: deploy a converted ONNX model behind a REST API (e.g. FastAPI) using an ONNX Runtime inference session
ml-ops · 6 steps · unrated
KServe: deploy a model as an InferenceService with autoscaling on Kubernetes
ml-ops · 5 steps · unrated
Export a PyTorch model to ONNX and run inference with ONNX Runtime
onnxruntime.ai/docs · 6 steps · unrated

Give your agent this knowledge — and 15,500+ more routes

One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp

Need this verified for your stack — or a route we don't have yet?

We author + individually verify a route for your exact task within 24h. Custom route — $25 · Teams: Pilot — $750/mo · all plans