NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev
pub.dev, #1807 most downloaded on pub.dev
Moved to flutter_edge_ai. This is the final release under the name flutter_gemma; new versions ship as flutter_edge_ai, part of Flutter Edge AI.
Latest stable
1.11.4
Last release 1 months ago
05 Oct 2026
Ships on a steady schedule
a new release about every 1 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
142 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
The codelabs carry the litert_embeddings.js that flutter_gemma_litertlm 1.8.4 ships by @DenisovAV in #562
Full Changelog: v1.11.0...v1.11.4
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Full Changelog: https://github.com/DenisovAV/flutter_edge_ai/compare/v1.11.0...v1.11.4
flutter_edge_ai; this is the final release under the name flutter_gemma.New flutter-gemma-diagnostics agent skill for flutter_gemma_diagnostics.
flutter-gemma-diagnostics agent skill for flutter_gemma_diagnostics.Web setup pins @mediapipe/tasks-genai 0.10.29, @litert-lm/core 0.17.1, ORT-web 1.30.0, Transformers.js 4.3.0.
@mediapipe/tasks-genai 0.10.29, @litert-lm/core 0.17.1, ORT-web 1.30.0, Transformers.js 4.3.0.The built-in AI skill describes flutter_gemma_builtin_ai 0.3.0: Windows, Linux and setup.
flutter_gemma_builtin_ai 0.3.0: Windows, Linux and setup.LiteRT-LM v0.17.0 (native-v0.17.0): litertlm 1.7.0, speech 0.5.1 by @DenisovAV in #522
Full Changelog: v1.8.3...v1.11.0
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.8.3...v1.11.0
EmbeddingModel.activeBackend: getActiveEmbedder(preferredBackend:) no longer goes unremarked.implements EmbeddingModel: add activeBackend and isClosed; extends inherits defaults.Add activationDataType to getActiveModel; float32 fixes wrong digits on some GPUs.
activationDataType to getActiveModel; float32 fixes wrong digits on some GPUs.New initialize(embeddingTokenizers:) — register one or embeddings throw; engines no longer bundle a tokenizer.
initialize(embeddingTokenizers:) — register one or embeddings throw; engines no longer bundle a tokenizer.web/rag/ build from the published archive.FunctionGemma on .litertlm answers a tool result instead of repeating the call.
.litertlm answers a tool result instead of repeating the call.fix(litertlm): don't clamp maxTokens on NPU, and say which models the NPU runs by @DenisovAV in #508
Full Changelog: v1.8.2...v1.8.3
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.8.2...v1.8.3
.litertlm on iOS wrapping every prompt in turn markers twice; deprecate StopTokenFilter.docs(website): full content audit + Built-in AI page + Engines nav group by @DenisovAV in #455
Full Changelog: v1.6.5...v1.8.2
dart run skills@ get --all teaches your AI assistant this package.Add VectorStoreRepository.flush(); custom implementations must declare it (#492).
VectorStoreRepository.flush(); custom implementations must declare it (#492).Whisper output language on getActiveStt and transcribe (#500).
getActiveStt and transcribe (#500).SpeechRecognizer implementations: transcribe gained language: and the type gained a language field.Example: LFM2.5-230M and the fromHuggingFace install path.
fromHuggingFace install path.Fix createChat dropping tools — function calling on every non-FFI engine.
createChat dropping tools — function calling on every non-FFI engine.@litert-lm/core setup snippet to 0.17.0.Fix web sessions failing right after install because the active model was only half-saved.
macOS setup snippet is now a thin shim; the staging logic ships with flutter_gemma_litertlm (#457).
flutter_gemma_litertlm (#457).kotlinx.coroutines keep from the Android consumer rules so R8 can shrink them (#486).Hugging Face install (#454): resolveHuggingFace / one-call installModel(…).fromHuggingFace(repo), with engines auto-registering their resolver.
resolveHuggingFace / one-call installModel(…).fromHuggingFace(repo), with engines auto-registering their resolver.feat(builtin-ai): web arm via Chrome Prompt API (LanguageModel) — 0.2.0 by @DenisovAV in #446
Full Changelog: v1.6.4...v1.6.5
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.6.4...v1.6.5
InferenceChat flag, not a hardcoded gemma4 check (no behavior change).fix(core): stop claiming background_downloader's updates stream from the host by @DenisovAV in #450
Full Changelog: v1.6.2...v1.6.4
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.6.2...v1.6.4
flutter_gemma_mediapipe still needs 16.0 (#441).Download updates are scoped to our own task group; FileDownloader().updates stays the host's (#445).
FileDownloader().updates stays the host's (#445).docs(website): vision/audio per-encoder backend (1.5.9 / litertlm 1.4.2) by @DenisovAV in #430
Full Changelog: v1.5.9...v1.6.2
ModelFileType.onnx install is fileless — Transformers.js owns the repo, install just sets it active.getActiveModel compares every runtime param before reusing the cached model.
getActiveModel compares every runtime param before reusing the cached model.getActiveModel calls no longer share a model built for other params.FilterField.validateSchema — rejects duplicate field names, checked in release.FieldEquals / FieldRange semantics both stores must honour.Add ModelFileType.onnx + ONNX engine chat-format routing — enables the new flutter_gemma_onnx engine.
ModelFileType.onnx + ONNX engine chat-format routing — enables the new flutter_gemma_onnx engine.fix(litertlm): detect stream-callback ABI at runtime (LiteRT-LM v0.15.0) by @DenisovAV in #410
Full Changelog: v1.5.7...v1.5.9
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.7...v1.5.9
docs: Windows discrete GPU is fixed in litertlm 1.4.0 — the README said it was still broken.
chore(website): docs → flutter_gemma 1.5.6; document VoiceSession streamAudio by @DenisovAV in #420
🙏 Credit: the #391 fix was also submitted independently by @o-mid in #421, opened before #422 landed — thank you for the fix and the report.
Full Changelog: v1.5.6...v1.5.7
fix(agent): require flutter_gemma ^1.5.5 (onMaxToolTurns) by @DenisovAV in #418
Full Changelog: v1.5.5...v1.5.6
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.5...v1.5.6
consolidate: AgentLoop delegates its tool loop to core (core 1.5.5 + agent 0.2.2) by @DenisovAV in #417
Full Changelog: v1.5.4...v1.5.5
feat(agent): stream final-answer tokens in AgentLoop (VoiceSession parity) by @DenisovAV in #415
Full Changelog: v1.5.3...v1.5.4
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.3...v1.5.4
refactor(example): standard list-screen model selection for TTS + Voice Loop by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/411
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.2...v1.5.3
example: download progress on model-install screens + device-local LLM staging for the voice gate by @DenisovAV in https://github.com/DenisovAV/flutte
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.1...v1.5.2
feat: Whisper + Parakeet-CTC STT, int8 models, install-identity namespacing by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/406
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.5.0...v1.5.1
feat(genai): genai_primitives parallel input/output path (#181) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/363
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.4.2...v1.5.0
package:flutter_gemma/genai.dart — use ChatMessage with InferenceChat (#181).sendMessage/generateContent (+ streams) covering text, vision, audio, thinking, and tool calls (#181).activeModelSpec/activeEmbedderSpec/activeSttSpec/activeTtsSpec + getModelPath.getStorageInfo/getOrphanedFiles/cleanupStorage/performCleanup — surface real errors, not success-shaped defaults.FlutterGemma.rag namespace (add/search/removeDocument/stats/clear); plumb removeDocument (#390 audit).uninstallEmbedder/uninstallStt/uninstallTts (delete all files); route uninstallModel off the deprecated path.ModelSource + FileSystemService from the barrel (required public parameter types).FlutterGemmaPlugin as the low-level SPI tier; FlutterGemma facade is the canonical entry.docs: fix stale version pins + TTS README/CLAUDE coverage by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/397
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.4.1...v1.4.2
fix(litertlm): actionable error for GPU-only models on CPU + drop blanket CPU default (#390) by @DenisovAV in https://github.com/DenisovAV/flutter_gem
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.4.0...v1.4.1
installTts()/getActiveTts()/synthesize(), raw PCM output.RuntimeConfig.artifactPaths.chore(genkit): regenerate example generated_plugins.cmake by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/386
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.3.1...v1.4.0
flutter_gemma_speech runs a selectable ASR model (moonshine today) on all native platforms via installStt()/getActiveStt()/transcribe().$PWD-relative dir, not %LOCALAPPDATA% — model installed but not found at load.Docs: add community models to the README model list (SmolLM3-3B, Phi-4-mini-reasoning, Qwen2-VL, SmolVLM2, LLaVA-OneVision).
@litert-lm/core setup snippet to 0.14.0.fix(core): eliminate background_downloader temp-file leak + deterministic task IDs (#383) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.3.0...v1.3.1
docs: reflect 1.2.3 release version pins (website + CLAUDE.md + DESKTOP_SUPPORT.md) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/3
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.2.3...v1.3.0
chore(genkit): regenerate example generated_plugins.cmake by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/359
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.2.2...v1.2.3
.litertlm decoding before session teardown to avoid an ANR (#364, #373).} (#366).chat_template (#367)._TypeError (#367).parameters:{type:OBJECT} for no-argument FunctionGemma tools (#367).required:[] inside FunctionGemma items, as the template does (#367).<end_function_call> leaking into FunctionGemma chat text and history (#366).properties/items, else require it (#367).None the way the template's Python does (#367).None argument as null instead of the string "None" (#366).ToolChoice.required on FunctionGemma (#367).result:{json} (#367).fix(android): declare libvndksupport.so for GPU backend (#324) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/341
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.1.0...v1.2.2
android.builtInKotlin=false — apply KGP unless built-in Kotlin is on, so the plugin's Kotlin compiles (#360).fix(android): declare libvndksupport.so for GPU backend (#324) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/341
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.1.0...v1.2.1
POST_NOTIFICATIONS at runtime (#356).FOREGROUND_SERVICE_DATA_SYNC + service merge (#356).resume()'s bool, arm reattach watchdog (#355 #356).Add skillExecutors: to FlutterGemma.initialize + the SkillExecutorProvider/SkillExecutorRegistry seam for the new opt-in flutter_gemma_agent package.
skillExecutors: to FlutterGemma.initialize + the SkillExecutorProvider/SkillExecutorRegistry seam for the new opt-in flutter_gemma_agent package.libOpenCL.so (+ -car/-pixel ICDs) in the plugin manifest — completes the #324 Mali GPU fix (#349; 1.1.1 only opened the SP-HAL door).<|tool_call> tokens the browser runtime leaves unconverted, and guard a crash when the SDK returns content as a String.Migrate Android module to Built-in Kotlin — apply KGP only on AGP < 9, ready for AGP 9+ (#323).
downloadUpdatesStream/fileSystemService injection to FlutterGemma.initialize (#342, thanks @hughesyadaddy).Declare libvndksupport.so for the Android GPU backend — fixes Mali GPU hard-freeze on Android 12+ (#324).
libvndksupport.so for the Android GPU backend — fixes Mali GPU hard-freeze on Android 12+ (#324).Un-deprecate rag_sqlite: single-engine sqlite-vec/vec0 RAG (1.1.0) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/340
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.0.2...v1.1.0
Filter support: FilterSchema/FilterField/FilterFieldType + configure(FilterSchema) on VectorStoreRepository.filterSchema: to FlutterGemma.initialize (threaded to the vector store at registration).enableHnsw (no-op; vector search now runs inside the store engine).Add clearActiveInferenceIdentity/clearActiveEmbeddingIdentity (non-breaking defaults on ModelFileManager).
clearActiveInferenceIdentity/clearActiveEmbeddingIdentity (non-breaking defaults on ModelFileManager).DownloadError/DownloadException from flutter_gemma.dart.fix(#318): clamp maxTokens to 1024 + add maxOutputTokens by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/330
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.0.1...v1.0.2
maxOutputTokens on createSession/openSession/createChat/openChat to cap generation length (#318).maxTokens dartdoc: it's the context window (input + output), not reply length.1.0.1: restore NPU (#155) + fix empty cancelled chat turn (#325) + README/example fixes by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pu
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v1.0.0...v1.0.1
stopGeneration() — cancelled/empty responses are no longer recorded (#325).homepage to fluttergemma.dev. No code change.chore: pub.dev score 130→150 + WASM compatibility by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/317
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.5...v1.0.0
dart:io is off the web/wasm import graph.core/domain/platform_types.dart.large_file_handler ^0.5.0.Modular package split: core flutter_gemma + opt-in flutter_gemma_litertlm / flutter_gemma_mediapipe / flutter_gemma_embeddings / flutter_gemma_rag_qdr
flutter_gemma + opt-in flutter_gemma_litertlm / flutter_gemma_mediapipe / flutter_gemma_embeddings / flutter_gemma_rag_qdrant / flutter_gemma_rag_sqlite.FlutterGemma.initialize(inferenceEngines:, embeddingBackends:, vectorStore:) — register the opt-in packages you added; core registers none by default.Enable function calls for Gemma 4 E2B/E4B in example (#303) by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/305
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.4...v0.16.5
feat(0.16.3): Android Qualcomm NPU + qdrant-edge 0.7.1 by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/296
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.2...v0.16.4
/utf-8 to the MSVC plugin target.feat(0.16.3): Android Qualcomm NPU + qdrant-edge 0.7.1 by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/296
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.2...v0.16.3
PreferredBackend.npu): auto-extracts QNN dispatch libs from APK at runtime (#293).wal_options now native in upstream.Release 0.16.1 by @DenisovAV in https://github.com/DenisovAV/flutter_gemma/pull/291
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.1...v0.16.2
openSession()/openChat() run independent dialogues on one loaded model..litertlm inference via @litert-lm/core early preview (WebGPU/WASM, text-only).getActiveModel() after app restart (#227): mobile + web auto-restore from prefs.InferenceModel.activeBackend getter + NPU→GPU→CPU fallback on the FFI path with BackendInitException carrying per-attempt details.large_file_handler ^0.3.1 → ^0.4.0.fix: make iOS LiteRtLm artifacts Native-Assets strippable by @merlinnot in https://github.com/DenisovAV/flutter_gemma/pull/289
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.16.0...v0.16.1
ffed38a): NPU dispatch now available on Linux/macOS as well as Windows.libLiteRtLm.dylib with -Wl,-x so xcrun strip -x -S succeeds during release builds.%LOCALAPPDATA% env var is relative — falls back to USERPROFILE\AppData\Local then getApplicationSupportDirectory().Native LiteRT-LM prebuilts for flutter_gemma, built from LiteRT-LM 924e79c9 (v0.16.0) with LiteRT 0ff28117 .
Native LiteRT-LM prebuilts for flutter_gemma, built from LiteRT-LM 924e79c9 (v0.16.0) with LiteRT 0ff28117.
Consumed automatically by flutter_gemma_litertlm/hook/build.dart (Native Assets) at pub get time; SHA256-verified against the map baked into that hook. Previous release: native-v0.14.0 — there was no native-v0.15.0.
libStreamProxy resolves the shape at runtime, so both old and new hosts work.--define=litert_link_capi_so=true, a name upstream had deleted. Bazel accepts unknown defines silently, so the LiteRt runtime was being linked statically, which conflicts with the separately shipped WebGPU accelerator once Dawn became its own library. Corrected to litert_runtime_link_mode=dynamic + resolve_symbols_in_exec=false. That issue has been retracted.LiteRtDispatch.dll plus a version-matched OpenVino runtime (2026.3.0.dev20260622). The carried-forward pair shipped OpenVino 2026.2.0 against a runtime pinned to 2026.3.0, which is what broke backend=npu.libLiteRtDispatch_Qualcomm.so rebuilt from the derived LiteRT ref, and the ten QNN runtime libraries refreshed from the same QAIRT 2.44.0.260225. The stale pair failed with Qnn System library version 1.8.0 is mismatched. The minimum supported version is 1.11.0.libStreamProxy.dylib had been inheriting the build host's OS since native-v0.14.0 and shipped with minos 26.0; it is now built with -mmacosx-version-min=11.0.Engine initialized successfully, NPU engine_create in 498 ms.install_name_tool rewrite clean on every one (Native Assets re-runs it on each pub get); iOS minos 13.0, macOS 11.0; gpu_registry @executable_path patch present, basename dlopen absent.| Archive | Files |
|---|---|
litertlm-android_arm64.tar.gz |
19 — core + Qualcomm QNN NPU stack |
litertlm-ios_arm64.tar.gz |
4 |
litertlm-ios_sim_arm64.tar.gz |
4 |
litertlm-macos_arm64.tar.gz |
4 |
litertlm-linux_x86_64.tar.gz |
7 |
litertlm-linux_arm64.tar.gz |
7 |
litertlm-windows_x86_64.tar.gz |
28 — core + DXC runtime + Intel NPU stack |
SHA256 sums for every archive are in checksums_litertlm.txt.
Full Changelog: https://github.com/DenisovAV/flutter_gemma/compare/v0.15.3...v0.16.0
@Deprecated, removal in 1.0.searchSimilar(... filter: Filter(must: [...], should: [...], mustNot: [...])). Honored on native; silently ignored on Web.FileSystemService; legacy Documents/ reads kept as fallback.example: add TranslateGemma 4B translation demo via task-first home navigation (#177).
CPU-only by design — community .litertlm keeps EMBEDDING_LOOKUP in float32 for MediaPipe .task compatibility, and the LiteRT GPU partitioner can't cluster that layout. Tracked upstream at google-ai-edge/LiteRT-LM#1748.
Unified embedding on LiteRT C API + Dart FFI on all native platforms (#264).
Unified embedding on LiteRT C API + Dart FFI on all native platforms (#264).
LitertEmbeddingModel runs on Android, iOS, macOS, Linux, Windows via dart:ffi against the LiteRT C API. The LiteRT runtime is already shipped in the native bundle for inference accelerators — no new native dep.localagents-rag JVM lib, iOS TensorFlowLiteC pod + Swift tokenizer hierarchy, Desktop libtensorflowlite_c.{dylib,so,dll} tarball.TaskType.prefix is now the single source of truth for retrievalQuery / retrievalDocument prefix strings — fixes the cross-platform drift that caused #264 by construction.LiteRtLayout MSVC vs GCC/Clang bit-field ABI handled via dual-layout FFI structs (LiteRtLayoutPosix / LiteRtLayoutMsvc + View helper).Cross-platform RAG drift verified <0.003 on six platforms × two embedding models (Gecko 110M, EmbeddingGemma 300M):
| macOS | iOS Sim | iPhone | Pixel 8 | Linux T4 | Windows MSVC | |
|---|---|---|---|---|---|---|
| Gecko 64 climate↔warming | 0.9161 | 0.9161 | 0.9161 | 0.9168 | 0.9163 | 0.9163 |
| EmbeddingGemma 256 climate↔warming | 0.8695 | 0.8695 | 0.8695 | 0.8689 | 0.8668 | 0.8668 |
Full 18-test litertlm_ffi_test.dart integration suite green on macOS, Linux T4, Windows NPU VM (Intel Lunar Lake), Pixel 8.
EmbeddingInstallationBuilder.tokenizerFromNetwork/Asset/Bundled/File: removed the iOS-only iosPath / iosToken parameters. They were no-ops since 0.15.2 (same tokenizer on every platform now). Callers that omit them are unaffected; callers that pass them need to remove the named arg.See CHANGELOG.md and the migration story in the PR description for the full diff.
🪟 Windows Intel NPU end-to-end — PreferredBackend.npu on LunarLake/PantherLake. Native bundle ships Intel dispatch + OpenVino + TBB.
PreferredBackend.npu on LunarLake/PantherLake. Native bundle ships Intel dispatch + OpenVino + TBB.Message.withImages([...]).PreferredBackend.npu.enableSpeculativeDecoding parameter missing in FFI stub.See CHANGELOG.md for full details.
patchelf --add-needed libLiteRtLm.so on libLiteRtTopK{OpenCl,WebGpu}Sampler.so.Message.withImages([...]) for multi-image input, chat/Conversation session metrics via FFI, persistent prefix messages replayed on session rebuild after history truncation. Backward-compatible (Message.withImage(...) still works).temperature/topK/topP/seed are silently ignored when PreferredBackend.npu is selected — LiteRT-LM NPU executor only supports internal greedy sampling.LiteRtDispatch.dll), OpenVino runtime, TBB (~30 MB); FFI client passes dispatch_lib_dir + use_hw_masking_for_npu=false at engine_create so PreferredBackend.npu works on Intel LunarLake/PantherLake silicon without manual DLL placement.LiteRtLmFfiClient stub on web was missing the enableSpeculativeDecoding parameter — dart2js failed compilation when web target was actually built.build-litertlm-native-windows.yml workflow for Windows-only rebuilds.One column per month.