---
title: "Blog - Xybrid"
description: "Technical articles about on-device AI, edge inference, and building ML-powered applications that run locally on mobile and desktop."
url: "https://www.xybrid.ai/blog"
---

# Notes from the on-device frontier.

Technical deep-dives into on-device AI, edge inference, and building ML-powered applications that run anywhere.

19 posts · [RSS feed](https://www.xybrid.ai/blog/rss.xml)

- [On-Device AI: The Complete Guide to Running ML Models Locally](https://www.xybrid.ai/blog/on-device-ai-guide) — Everything you need to know about running machine learning models directly on mobile and desktop devices — privacy, latency, cost benefits, and how to get started.
  Mar 23, 2026 · Featured · Engineering · 12 min read
- [On-device LLMs in React Native (2026): Xybrid vs llama.rn vs React Native ExecuTorch](https://www.xybrid.ai/blog/react-native-on-device-llm) — Compare Xybrid, llama.rn and React Native ExecuTorch for running an LLM offline in React Native or Expo: install, models, platforms, speech, tool calling.
  Nov 14, 2026 · Engineering · 19 min read
- [Publishing ML Models as Bundles with xybrid-pack](https://www.xybrid.ai/blog/publishing-ml-models-as-bundles-xybrid-pack) — A packaging pipeline that turns raw model files into versioned, checksummed, cross-platform bundles hosted on HuggingFace. No more 'download the model and put it here.'
  Jul 17, 2026 · Engineering · 5 min read
- [Vendoring llama.cpp in a Rust Workspace (Lessons Learned)](https://www.xybrid.ai/blog/vendoring-llamacpp-in-rust-workspace) — The practical pain of embedding a C++ inference engine in a Rust monorepo — cross-compilation, Android fp16, think-tag stripping, and when to give up on upstream.
  Jul 14, 2026 · Engineering · 7 min read
- [model_metadata.json: A Declarative Schema for ML Model Execution](https://www.xybrid.ai/blog/model-metadata-json-declarative-schema) — How a single JSON file replaces custom inference scripts and makes any ML model self-describing. No more 'works on my machine.'
  Jul 10, 2026 · Engineering · 6 min read
- [Streaming LLM Tokens from Rust to Flutter in Real-Time](https://www.xybrid.ai/blog/streaming-llm-tokens-rust-to-flutter) — How we bridge real-time token streaming from a Rust inference engine to Flutter's reactive UI using flutter_rust_bridge callbacks.
  Jul 7, 2026 · Engineering · 6 min read
- [How We Made ONNX Runtime 6.8x Faster on Apple Silicon with CoreML](https://www.xybrid.ai/blog/onnx-runtime-6x-faster-apple-silicon-coreml) — Real benchmarks showing when Apple's Neural Engine helps (and when it hurts). Lessons from optimizing ML inference across execution providers.
  Jul 3, 2026 · Engineering · 6 min read
- [Whisper Speech Recognition as a Single Rust Binary](https://www.xybrid.ai/blog/whisper-speech-recognition-single-rust-binary) — Build a Whisper-powered transcription tool as a single Rust binary. Candle for pure-Rust inference. No runtime dependencies, works airgapped.
  Jun 30, 2026 · Tutorial · 5 min read
- [Why We Chose Rust Over Python for ML Inference](https://www.xybrid.ai/blog/why-rust-over-python-for-ml-inference) — Not training — inference. How Rust's zero-cost abstractions, lack of GIL, and FFI story make it the better choice for shipping ML to production devices.
  Jun 26, 2026 · Engineering · 7 min read
- [On-Device AI for Mobile Apps: A Developer's Guide to iOS and Android](https://www.xybrid.ai/blog/on-device-ai-mobile-ios-android) — How to add on-device AI to iOS and Android apps — comparing CoreML, ONNX Runtime, TensorFlow Lite, and llama.cpp. Practical guide with model sizes, performance benchmarks, and integration patterns.
  Jun 23, 2026 · Engineering · 12 min read
- [Edge AI: Why Edge-First Should Be Your Default Architecture](https://www.xybrid.ai/blog/edge-first-should-be-your-default) — On-device AI should be the starting position, not the optimization. The industry defaults to cloud out of habit, not necessity.
  Jun 19, 2026 · Engineering · 7 min read
- [Private AI: How to Run AI Models Without Sending Data to the Cloud](https://www.xybrid.ai/blog/private-ai-run-models-without-cloud) — How to run AI models privately on-device — no cloud APIs, no data leaving the device. Covers GDPR, HIPAA, and SOC 2 compliance, private LLMs, and practical implementation patterns.
  Jun 16, 2026 · Engineering · 10 min read
- [Building a Cross-Platform ML Inference SDK in Rust](https://www.xybrid.ai/blog/building-cross-platform-ml-inference-sdk-in-rust) — How we built a single Rust core that powers ML inference across CLI, Flutter, Swift, Kotlin, and Unity — and the architectural decisions that made it possible.
  Jun 12, 2026 · Engineering · 7 min read
- [How to Run LLMs Locally: A Complete Guide (2026)](https://www.xybrid.ai/blog/run-llm-locally-complete-guide) — How to run large language models locally on your laptop, desktop, or phone — llama.cpp, Ollama, ONNX Runtime, and on-device options compared. No cloud API needed.
  Jun 9, 2026 · Engineering · 12 min read
- [One Codebase, Five Platforms: Shipping ML to Flutter, Swift, Kotlin, Unity & CLI](https://www.xybrid.ai/blog/one-codebase-five-platforms-ml-flutter-swift-kotlin-unity) — How UniFFI, flutter_rust_bridge, and C FFI let us write ML inference once in Rust and bind it to five platform SDKs. The cross-platform FFI playbook.
  Jun 5, 2026 · Engineering · 8 min read
- [Run AI Models On-Device — Zero Config, Five Minutes](https://www.xybrid.ai/blog/run-ai-models-on-device-zero-config) — CLI, Rust, Flutter, Swift, Kotlin, Unity — run 25+ ML models on-device with one command. No tensor shapes, no preprocessing scripts.
  Jun 2, 2026 · Announcement · 3 min read
- [Add Text-to-Speech to Your Flutter App in 15 Minutes](https://www.xybrid.ai/blog/add-text-to-speech-to-flutter-app-in-15-minutes) — A step-by-step guide to adding high-quality, on-device TTS to a Flutter app using Xybrid and the Kokoro model. No cloud APIs, no API keys, no per-request costs.
  Apr 6, 2026 · Tutorial · 8 min read
- [Edge AI vs Cloud AI: When to Run Models On-Device](https://www.xybrid.ai/blog/edge-vs-cloud-inference) — A practical decision framework for choosing between on-device and cloud-based AI inference, with cost analysis, comparison tables, and real-world use cases.
  Mar 20, 2026 · Engineering · 10 min read
- [Building a Voice Agent That Runs Entirely On-Device](https://www.xybrid.ai/blog/building-voice-agent-on-device) — A step-by-step tutorial for building an on-device voice agent using Whisper, a local LLM, and Kokoro TTS — no cloud APIs, no internet required.
  Mar 17, 2026 · Tutorial · 11 min read
