Install llamadart

For Genkit or Flutter Edge AI integration setup, see Choose an integration.

Requirements#

• Dart SDK >= 3.10.7
• Flutter SDK >= 3.38.0 (if you build Flutter apps)
• Flutter iOS apps: deployment target 16.4 or newer
• Flutter macOS apps: deployment target 14.0 or newer
• Windows: nothing extra for llama.cpp and LiteRT-LM, which bundle the Visual C++ runtime DLLs they need. Machines that run the opt-in stable_diffusion runtime need the latest Microsoft Visual C++ v14 Redistributable (x64), which stock Windows Server lacks; see Image generation.

Add the package#

dependencies:
  llamadart: ^0.17.3

Then resolve packages:

dart pub get
# or
flutter pub get

Flutter iOS and macOS setup#

Set the deployment target (iOS 16.4 or newer, macOS 14.0 or newer), then add the runtime companion packages you need so Swift Package Manager links the Apple XCFrameworks:

dependencies:
  llamadart: ^0.17.3
  llamadart_llama_cpp_flutter: ^0.17.1 # GGUF / llama.cpp
  llamadart_litert_lm_flutter: ^0.17.1 # Apple .litertlm / LiteRT-LM targets
  llamadart_stable_diffusion_flutter: ^0.17.1 # Apple image generation, opt-in

Companions use the core's MAJOR.MINOR; pub refuses a mismatched pair. Apple setup covers deployment targets, companion versions and checks, the privacy manifest, Intel Macs, the SwiftPM bootstrap for a fresh macOS build, and the LiteRT-LM build phase.

Web#

Web apps must load the WebGPU bridge script in their web/index.html; the package does not inject it. From the app root, run:

dart run llamadart:web_setup

It vendors the pinned bridge assets into web/webgpu_bridge/, verifies their checksums and adds the bootstrap to web/index.html; rerun it after upgrading llamadart. See Add the bridge to your app.

AI agent skills#

The package ships agent skills that teach coding agents llamadart's APIs. After pub get, run this from your app's root and pick the skills and agent to install them for:

dart run skills@ get

Rerun it after upgrading llamadart to update the installed skills.

Verify it works#

Run the Quickstart example with maxTokens: 1. If the runtime initializes and the model loads, your setup is complete.

What happens on first build#

On the first dart run / flutter run for a native target, llamadart:

1. Detects platform and architecture.
2. Resolves matching runtime artifacts from leehack/llamadart-native and leehack/litert-lm-native.
3. Wires them into your app through native assets. Flutter iOS builds use SwiftPM-linked XCFrameworks when the matching companion packages are present; without the LiteRT-LM companion, Flutter macOS LiteRT-LM keeps its libraries in the hook cache and needs the build phase in the app. The opt-in image generation runtime comes from leehack/stable-diffusion-native the same way.

No local C++ toolchain setup is required for consumers.

Customize native runtimes#

Native builds bundle llama.cpp and LiteRT-LM by default; image generation is opt-in. To ship only one model format, or to test another native build, set hooks.user_defines in your pubspec.yaml:

hooks:
  user_defines:
    llamadart:
      llamadart_native_runtimes: [llama_cpp] # or [litert_lm]
      # Compatibility testing only; omit to use the tested pin.
      # llamadart_native_tag: v0.8.0-1

An override tag names a leehack/llamadart-native release and must be explicit; the accepted forms are in Override the llama.cpp release. An override does not regenerate the Dart bindings, so its binary must stay ABI-compatible with the default leehack/llamadart-native@v0.8.0-1 runtime. Do not point a core before 0.17.1 at native v0.8.0 or later: its bindings give mtmd_helper_init_opt 24 bytes, and v0.8.0 writes past them.

Every key, per-target backend and Android CPU variant selection, local bundle paths, and fallback rules: Configuring native backend modules, including what happens when a requested backend is not bundled. How the hook resolves runtimes: Native runtime configuration. Apple SwiftPM path: Apple setup. Setup check: Diagnose setup.