Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
LiteRT-LM Alternatives
Similar projects and alternatives to LiteRT-LM
-
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
-
omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
-
android-sdk-sources-for-api-level-1
This is only a backup for Android SDK Sources for API Level 1 [Android 1.0].
-
gallery
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
-
sherpa-onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
-
gemma4-heretical
Abliterated Gemma 4 31B for Ollama and MLX — one-command setup with correct chat template fix
-
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a better LiteRT-LM alternative or higher similarity.
LiteRT-LM discussion
LiteRT-LM reviews and mentions
Posts with mentions or reviews of LiteRT-LM.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2026-10-10.
-
Cleanup Walk: an Android app that turns screen time into a neighborhood cleanup.
Open-source AI: Gemma 3n E2B. It's Google's open-weight multimodal model, running entirely on the phone through LiteRT-LM (Apache 2.0). Each scan sends the camera photo plus a fixed prompt, and Gemma replies in a strict, parseable format:
-
Your AI, Your Device, Your Data - Introducing Aide
For day-to-day use, Aide runs the E2B and E4B weights fully on-device through LiteRT-LM. These small variants are built for mobile and edge, and they are quick enough to back the keyboard transforms, the voice loop, and chat without a network round-trip. The same multimodal model reads an image in chat, drives native function calling for the tool dispatcher, and exposes its reasoning trace through the thinking chip. For most daily interactions, E2B and E4B carry the whole experience locally.
-
Gemma 4 on iPhone
Thanks! Although, I can't claim any credit for it. I just spent a day gluing what other people have built. Huge props to the Gemma team for building an amazing model and also an inference engine that's focused for edge devices [0]
[0] https://github.com/google-ai-edge/LiteRT-LM
- Add NPU support for AICore for Gemma4 model
- A C++ library to efficiently run language models across edge platforms
- A C++ library to efficiently run Gemma-3N across various platform
-
A note from our sponsor - AppSignal
www.appsignal.com | 10 Oct 2026
Stats
Basic LiteRT-LM repo stats
6
6,628
9.9
about 20 hours ago
google-ai-edge/LiteRT-LM is an open source project licensed under Apache License 2.0 which is an OSI approved license.
The primary programming language of LiteRT-LM is C++.
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com