I take ML / CV / VLM models and make them run on phones, tablets and AR headsets — fast, small, and fully offline. Writing as MLBoy on Zenn, Medium and Qiita — same person everywhere.
coreai-model-zoo — 60+ verified Core AI models · CoreAIKit — run them in one line of Swift · devicemark — on-device LLM leaderboard for iPhone · The Art of Core AI — the textbook (JA, free)
CoreML-Models ⭐1.8k · LiteRT-Models · VLMKit · ex-Ultralytics (YOLO on mobile) · 10 apps on the App Store · Osaka, Japan (JST)
250+ converted models on Hugging Face · member of litert-community (Google LiteRT) and coreai-community
| Ship a model on-device | PyTorch / ONNX → Core ML or LiteRT, production-ready, not a demo |
| Make it fast | Latency and memory — quantization, palettization, ANE / GPU / NPU tuning |
| Real-time camera & video | Detection, tracking, segmentation at frame rate |
| On-device VLM / LLM | Structured extraction and generation, fully offline |
| Train or fine-tune | Building the model for the target device, not only deploying someone else's weights |
Small, well-scoped pieces are welcome as well as longer engagements.
📧 rockyshikoku@gmail.com — I reply within a day 🌐 john-rocky.github.io — shipped apps, past work, details
Freelance through Pebble Inc. (Osaka, JST) — currently taking projects. Remote; occasional travel is fine.