LiteRT-LM

Google AI Edge Portal introduces new LLM benchmarking and debugging capabilities, enabling performance optimization across over 120 Android devices with key metrics like initialization time and decode speed analysis, plus visualization tools.

Gemma 4 12B combined with Google AI Edge enables local execution on laptops, supporting code generation, voice editing, and OpenAI-compatible APIs on macOS. This setup facilitates on-device agentic workflows with a 60%+ quality boost in instruction following while ensuring offline privacy.

Google AI Edge introduces LiteRT-LM, an optimized inference engine for deploying Gemma 4 models on edge devices, supporting Android, iOS, and web platforms with GPU inference reaching 76 tokens/sec and Multi-Token Prediction delivering up to 2.2x speedup.

Google 提出 TLMs（Tiny Language Models）与 LiteRT-LM 框架，支持在边缘设备上高效部署轻量级 LLM 和自主 Agent，兼顾低延迟、隐私保护与离线能力。