Models

flutter_gemma supports Gemma 4, Gemma3n, FastVLM, Gemma 3, FunctionGemma, Qwen3, Qwen 2.5, Phi-4, DeepSeek R1, SmolLM and more. Desktop platforms (macOS, Windows, Linux) require the .litertlm model format.

Model file types#

Flutter Gemma supports different model file formats, grouped into two types based on how chat templates are handled.

Type 1: MediaPipe-managed templates#

• .task files: MediaPipe-optimized format for mobile (Android/iOS).
• .litertlm files: LiteRT-LM format for Android, iOS, and Desktop.

Both formats have identical behavior — chat templates are handled internally.

Type 2: Manual template formatting#

• .bin files: standard binary format.
• .tflite files: LiteRT format (formerly TensorFlow Lite).

Both formats require manual chat template formatting in your code.

Format by platform#

¹ iOS .litertlm runs on the FFI engine — vision and audio supported on physical devices. The Simulator stays CPU-only because Metal sim has a 256 MB single-allocation cap.

Model capabilities#

ModelType reference#

When installing models, specify the correct ModelType:

Usage example:

// Gemma models
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromNetwork(url).install();

// DeepSeek models
await FlutterGemma.installModel(modelType: ModelType.deepSeek)
  .fromNetwork(url).install();

// Phi-4 (uses general type)
await FlutterGemma.installModel(modelType: ModelType.general)
  .fromNetwork(url).install();

Supported models & platforms#

Installation sources#

// Network — .litertlm is the cross-platform default (Android/iOS/Desktop).
// For mobile-only or web-only apps you can substitute a .task URL.
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromNetwork('https://example.com/model.litertlm', token: 'optional')
  .install();

// Flutter assets
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromAsset('assets/models/model.litertlm')
  .install();

// Native bundle
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromBundled('model.litertlm')
  .install();

// External file (native only)
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromFile('/path/to/model.litertlm')
  .install();

Source capabilities#

Android foreground service (large downloads)#

Android has a 9-minute background execution limit. For large models (>500MB) the plugin auto-detects and uses a foreground service (shows a notification) to bypass it:

// Auto-detect based on file size (>500MB = foreground) — DEFAULT
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromNetwork(url)  // foreground: null (auto-detect)
  .install();

// Force foreground mode
await FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromNetwork(url, foreground: true)
  .install();

iOS uses native URLSession which handles long downloads automatically — no foreground service needed.

Cancelling downloads#

import 'package:flutter_gemma/core/model_management/cancel_token.dart';

final cancelToken = CancelToken();

final future = FlutterGemma.installModel(modelType: ModelType.gemmaIt)
  .fromNetwork(url)
  .withCancelToken(cancelToken)
  .withProgress((progress) => print('Progress: $progress%'))
  .install();

// Cancel from elsewhere (e.g. user pressed a cancel button)
cancelToken.cancel('User cancelled download');

try {
  await future;
} catch (e) {
  if (CancelToken.isCancel(e)) {
    print('Download was cancelled by user');
  }
}

CancelToken cancels all files in multi-file downloads (e.g. embedding model + tokenizer), works on mobile + web, and throws DownloadCancelledException.

Text embedding models#

All embedding models generate 768-dimensional vectors. The numbers in names (64/256/512/1024/2048) indicate maximum input sequence length in tokens, not embedding dimension. See Embeddings & RAG for usage.

Performance (Android Pixel 8, GPU acceleration):

• Gecko 64: ~109 ms/doc embedding, 130 ms search (fastest — 2.6× faster than EmbeddingGemma).
• EmbeddingGemma 256: ~286 ms/doc embedding, 342 ms search (more accurate — 300M vs 110M params).