google-ai-edge/LiteRT-LM

C++6.3K stars688 forks+501 today

Topics

#edge-ai#on-device-ai#on-device-llm

What it does

LiteRT-LM is Google's open-source inference framework for deploying large language models on edge devices, offering cross-platform support and hardware acceleration to enhance performance.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-04-25

Creator kit

Hook

Experience the power of Gemma 4 on your edge device with LiteRT-LM, Google's cutting-edge inference framework for deploying large language models. #AIEdge #GoogleAI

Content angles

Creating tutorials on how to deploy Gemma 4 using LiteRT-LM
Analyzing performance benchmarks and hardware requirements for different devices
Exploring the multi-modality features of LiteRT-LM

Who should care

Developers, AI researchers, and tech enthusiasts interested in edge computing and large language models.