Repository Issue Activity (beta)

#933 Feature Request: Add message actions (Copy, Edit, Regenerate)

#932 support for gemma4:12b-it-qat

#931 Feature request: Enable MTP (speculative decoding) by default on model load

#930 Feature request: Add quick toggle for thinking/reasoning mode on the input field

#929 [BUG] Chat screen not automatically scrolling

#57 [Support]: personal data agentic usecases

#557 Bug: "Failed to create engine" (LiteRT) error when loading Gemma-4-E4B-it

#924 I'm excited 🥰 and waiting 🙏🏼 for Edge Gallery App when releases for Windows (PC) users, any plan for future release???

#921 Bring back inference stats to AI Chat

#945 [BUG] Can't delete skills on MacOS client

#548 Failed to create engine on Exynos 2600 (Galaxy S26 SM-S942N) - All models affected

#920 Cant use npu and app get crashed

#941 gemma4 12b not avaliable on a m5（16g） device

#934 GPU acceleration not working for A12Z Gemma-4-E2B-it

#882 [BUG] "Failed to create engine" on Samsung Galaxy S26 (Exynos variant)

#430 Publish on F-Droid

#736 App stuck on Initialising model

#887 [FEATURE]:Unify LiteRT Runtime for LLMs and On-Device Diffusion Models

#431 [Bug]: GPU Inference Failure (Status 13) - Gemma3-1B-IT - LiteRT Executor

#910 [Support]: GPU Acceleration On A55 not working, Bugs out.

#909 Trying to enable speculative decoding on the GPU crashes the app on my Galaxy Note20

#907 4096 token context limit on imported models is too low

#906 App should auto-detect device specs and choose best defaults

#908 Feature request: image generation

#685 BUG: " Issue of Google's Gemma Edge Gallery AI "