On-device AI for every platform.
Run LLMs, vision, speech-to-text, and text-to-speech locally. Private, offline, fast.
One SDK for iOS, Android, Flutter, React Native, Web, and more — with Hexagon NPU acceleration on Snapdragon.

RunAnywhere lets you add AI features to your app that run entirely on-device — no cloud, no latency, no data leaving the device:

• LLM Chat — Llama, Qwen, Gemma, Phi, LFM, Mistral, and more
• Vision (VLM) — image understanding and captioning
• Speech-to-Text — Whisper- and Moonshine-based transcription
• Text-to-Speech — neural voice synthesis
• Voice Assistant — full STT → LLM → TTS pipeline

One API spans iOS, Android, Flutter, React Native, and Web, and routes to the best engine on each device: Core ML on Apple, WebGPU in the browser, llama.cpp everywhere as a fallback, and the Hexagon NPU on Snapdragon.

QHexRT is RunAnywhere's inference runtime for the Qualcomm Hexagon NPU. It runs LLM, vision, speech, and text-to-speech models directly on the Snapdragon NPU (Hexagon v79 / v81) and ships as a built-in accelerator: your app calls the same loadModel and generate, and it uses the NPU automatically on supported devices.

• Runs LLM, VLM, speech-to-text, and text-to-speech on the NPU, including text-to-speech, which other runtimes run on the CPU.
• Runs Mixture-of-Experts and hybrid-attention models on the NPU (Phi-tiny-MoE, Qwen3.5).
• Fast prefill and low time-to-first-token, with context that extends past the compiled window.
• Prebuilt model bundles published on Hugging Face; the SDK downloads the one matching the device.

Measured on a Samsung Galaxy S25 (Snapdragon 8 Elite, Hexagon v79):

Available on the Kotlin, Flutter, and React Native SDKs. Snapdragon (Android arm64) only.

Text Generation LLM inference, 100% on-device		Voice AI STT → LLM → TTS pipeline, fully offline
Image Generation On-device diffusion model		Visual Language Model Vision + language understanding on-device

All SDKs ship on one version line, currently 0.20.11. Pin the same version across the core package and its backends. See Releases for what is published today.

import RunAnywhere
import LlamaCPPRuntime

LlamaCPP.register()
try RunAnywhere.initialize()

var load = RAModelLoadRequest()
load.modelID = "smollm2-360m"
load.category = .language
load.framework = .llamaCpp
_ = await RunAnywhere.loadModel(load)

var req = RALLMGenerateRequest()
req.prompt = "What is the capital of France?"
let result = try await RunAnywhere.generate(req)
print(result.text)

Install via Swift Package Manager — add the package URL:

https://github.com/RunanywhereAI/runanywhere-sdks

Products: RunAnywhere, RunAnywhereLlamaCPP, RunAnywhereONNX, RunAnywhereMLX.

Documentation · Source

import ai.runanywhere.proto.v1.ModelCategory
import ai.runanywhere.proto.v1.SDKEnvironment
import com.runanywhere.sdk.llm.llamacpp.LlamaCPP
import com.runanywhere.sdk.public.RunAnywhere
import com.runanywhere.sdk.public.extensions.*
import com.runanywhere.sdk.public.types.RAModelInfo
import com.runanywhere.sdk.public.types.RAModelLoadRequest

LlamaCPP.register()
RunAnywhere.initialize(
    context = this,
    environment = SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT,
)

val modelId = "smollm2-360m-instruct-q8_0"
RunAnywhere.downloadModelStream(RAModelInfo(id = modelId)).collect { /* progress */ }
RunAnywhere.loadModel(
    RAModelLoadRequest(model_id = modelId, category = ModelCategory.MODEL_CATEGORY_LANGUAGE),
)

val result = RunAnywhere.generate("What is the capital of France?")
println(result.text)

Install via Gradle (Maven Central):

dependencies {
    implementation("io.github.sanchitmonga22:runanywhere-sdk:0.20.11")
    implementation("io.github.sanchitmonga22:runanywhere-llamacpp:0.20.11")
    // Optional: STT / TTS / VAD
    // implementation("io.github.sanchitmonga22:runanywhere-onnx:0.20.11")
}

Documentation · Source

import { RunAnywhere, SDKEnvironment } from '@runanywhere/core';
import { LlamaCPP } from '@runanywhere/llamacpp';

await RunAnywhere.initialize({ environment: SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT });
LlamaCPP.register();

await RunAnywhere.downloadModel('smollm2-360m');
await RunAnywhere.loadModel('smollm2-360m');

const result = await RunAnywhere.generate('What is the capital of France?');
console.log(result.text);

Install via npm:

npm install @runanywhere/core@0.20.11 @runanywhere/llamacpp@0.20.11

Documentation · Source

import 'package:runanywhere/runanywhere.dart';
import 'package:runanywhere_llamacpp/runanywhere_llamacpp.dart';

await RunAnywhere.initialize();
LlamaCpp.register();

await RunAnywhere.downloadModel('smollm2-360m');
await RunAnywhere.llm.load('smollm2-360m');

final response = await RunAnywhere.llm.chat('What is the capital of France?');
print(response);

Install via pub.dev:

dependencies:
  runanywhere: ^0.20.11
  runanywhere_llamacpp: ^0.20.11
  # runanywhere_onnx: ^0.20.11   # STT, TTS, Voice

Documentation · Source

import { RunAnywhere, SDKEnvironment } from '@runanywhere/web';
import { LlamaCPP } from '@runanywhere/web-llamacpp';

await RunAnywhere.initialize({
  environment: SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT,
});
await LlamaCPP.register({ acceleration: 'auto' });
await RunAnywhere.completeServicesInitialization();

await RunAnywhere.loadModel({ modelId: 'qwen2.5-0.5b' });

const result = await RunAnywhere.generate({
  prompt: 'What is the capital of France?',
});
console.log(result.text);

Install via npm:

npm install @runanywhere/web@0.20.11 @runanywhere/web-llamacpp@0.20.11

Source

from runanywhere import RunAnywhere

with RunAnywhere() as ra:
    llm = ra.load_llm("qwen2.5-0.5b")
    print(llm.generate_text("What is the capital of France?"))

Install via pip:

pip install runanywhere==0.20.11

Source

Prebuilt bundles on Hugging Face; the SDK downloads the bundle matching the device.

Browse all models on Hugging Face

The Android, Flutter, and React Native apps include an NPU section that detects Hexagon arch and runs LLM, vision, speech, and TTS on the NPU.

Minimal projects to get up and running on each platform:

Real-world projects built with RunAnywhere. Each ships as a standalone app you can build and run.

• Android Use Agent — on-device autonomous Android agent that reads the screen and controls the phone with an on-device LLM
• On-Device Browser Agent — Chrome extension that automates browser tasks on-device with WebLLM and WebGPU
• Swift Starter App — SwiftUI app with LLM chat, STT, TTS, and a full voice pipeline
• Linux Voice Assistant — on-device voice pipeline (VAD → STT → LLM → TTS) in one C++ binary for Raspberry Pi 5, x86_64, and ARM64
• OpenClaw Hybrid Assistant — on-device VAD, STT, and TTS with cloud LLM reasoning
• YapRun — on-device dictation for iOS/macOS

A single C/C++ core (runanywhere-commons) behind a C ABI, with thin platform SDKs on top and a plugin registry that selects the best engine per device (llama.cpp, ONNX/sherpa, Core ML, Metal, and QHexRT on the Hexagon NPU). Business logic lives in the core, so one fix lands on all SDKs.

runanywhere-sdks/
├── sdk/
│   ├── runanywhere-swift/          # iOS/macOS SDK
│   ├── runanywhere-kotlin/         # Android SDK
│   ├── runanywhere-web/            # Web SDK (WebAssembly / WebGPU)
│   ├── runanywhere-react-native/   # React Native SDK
│   ├── runanywhere-flutter/        # Flutter SDK
│   ├── runanywhere-python/         # Python SDK (pybind11 over the C core)
│   ├── runanywhere-electron/       # Electron / Node (Windows preview)
│   ├── runanywhere-cli/            # rcli command-line tool
│   └── runanywhere-commons/        # Shared C/C++ core
│
├── engines/                        # Pluggable inference backends
├── examples/                       # Sample apps
├── Playground/                     # Real-world reference apps
└── docs/gifs/                      # Demo media assets

Hexagon NPU: Snapdragon with Hexagon v79 / v81 (Snapdragon 8 Elite class), Android arm64.
Memory: 2 GB minimum, 4 GB+ recommended for larger models.

We welcome contributions. See the Contributing Guide for details.

git clone https://github.com/RunanywhereAI/runanywhere-sdks.git
cd runanywhere-sdks

# Doctor / setup helpers
./run doctor
./run setup

# Build native XCFrameworks for local Swift development
./sdk/runanywhere-swift/scripts/build-core-xcframework.sh

# Run the iOS sample app
cd examples/ios/RunAnywhereAI
open RunAnywhereAI.xcodeproj

• Docs: docs.runanywhere.ai
• Discord: Join our community
• Issues: GitHub Issues
• Email: founders@runanywhere.ai
• Twitter: @RunanywhereAI

RunAnywhere License (Apache 2.0 based, with additional commercial-use terms).
See LICENSE for details.