NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev
pub.dev, #2056 most downloaded on pub.dev
Moved to flutter_edge_ai_litertlm. This is the final release under the name flutter_gemma_litertlm; new versions ship as flutter_edge_ai_litertlm, part of Flutter Edge AI.
Latest stable
1.8.6
Last release 1 months ago
05 Oct 2026
Ships fairly regularly
a new release about every 1 weeks
Nearly every release is documented
notes for 30 of 30 stable releases
Nothing withdrawn
no release was ever pulled
5 months old
31 releases · first in 2026
Drag across the ruler to compare, or tap a release to open it.
Moved to flutter_edge_ai_litertlm; this is the final release under the name flutter_gemma_litertlm.
flutter_edge_ai_litertlm; this is the final release under the name flutter_gemma_litertlm.Web setup pins @litert-lm/core 0.17.1.
@litert-lm/core 0.17.1.Web reports the accelerator embeddings ran on, and whether it was fully accelerated.
activeBackend no longer claims NPU on macOS, Linux, iOS or non-Qualcomm Android.Your coding agent can read these notes before it upgrades. Set up the MCP server →
One column per month.
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
activationDataType to the engine; float32 fixes wrong digits on some GPUs.docs(website): full content audit + Built-in AI page + Engines nav group by @DenisovAV in #455
Full Changelog: v1.6.5...v1.8.2
A chat stopped mid-reply answered every later message with nothing (#325).
Google Play no longer rejects apps over 16 KB page sizes (#529).
@litertjs/core 2.5.3.flutter_gemma_embeddings; asks core for a tokenizer, so register embeddingTokenizers:.Native runtime native-v0.17.0-a: tool calls no longer crash the app.
native-v0.17.0-a: tool calls no longer crash the app..litertlm takes the runtime's tool path — needs core 1.8.4.Native runtime: LiteRT-LM v0.17.0 (native-v0.17.0).
native-v0.17.0).CreateTensorBufferFromHostMemory status 3.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
Web: move @litert-lm/core 0.14.0 -> 0.17.0.
@litert-lm/core 0.14.0 -> 0.17.0.maxOutputTokens now caps generation instead of being ignored.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
Docs: the README and library docs show the engine-carried resolver and the one-call fromHuggingFace(repo) install.
fromHuggingFace(repo) install.Add LitertlmManifestResolver: manifest-driven Hugging Face install for repos shipping litertlm_manifest.json, auto-registered from LiteRtLmEngine (#45
LitertlmManifestResolver: manifest-driven Hugging Face install for repos shipping litertlm_manifest.json, auto-registered from LiteRtLmEngine (#454).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
LiteRtEmbeddingBackend (moved from flutter_gemma_embeddings).tokenizerFactory descriptor field; byte-identical vectors, no API change.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
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
libStreamProxy.dylib to 11.0 instead of the build host's.@litert-lm/core 0.14.0 (the 0.16.0 npm publish ships no dist/).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
.litertlm models run on CPU (#390).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
LiteRtBindings) for embeddings/speech; own web litert.js.Migrate FFI to LiteRT-LM v0.14.0 — native per-session sampler (opaque session-config); native-v0.14.0.
@litert-lm/core 0.12.1 → 0.14.0 (text path; API-compatible).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
Guard native cancel against a freed conversation — fixes a use-after-free SIGSEGV on close-mid-stream (#379).
Create the native conversation off the main isolate to avoid ANRs on multimodal models (#365).
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
maxTokens up to 1024 (min context for .litertlm) to fix the DYNAMIC_UPDATE_SLICE crash (#318).maxOutputTokens (session + chat) via native set_max_output_tokens; skipped on NPU.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
PreferredBackend.npu on Android (Qualcomm) + Windows (Intel): native-v0.13.1-a restores the NPU dispatch libs omitted from 1.0.0 (#155).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 mobile lib for a wasm-clean web graph.Initial release: LiteRT-LM (.litertlm) on-device inference engine for flutter_gemma via dart:ffi.
.litertlm) on-device inference engine for flutter_gemma via dart:ffi.LiteRtLmEngine (InferenceEngineProvider). Owns the shared LiteRT-LM native library.@litert-lm/core, early preview).