LiteRT-LM
PulseAugur coverage of LiteRT-LM — every cluster mentioning LiteRT-LM across labs, papers, and developer communities, ranked by signal.
-
Gemma 4 12B struggles with audio attention on large prompts
Users are encountering issues with Google's Gemma 4 12B unified model, which is designed to process audio, vision, and text simultaneously. While the model responds well to audio with short text prompts, it appears to l…
-
iPhone LLM benchmark: Neural Engine beats GPU in sustained performance
On-device LLM performance on the iPhone 17 Pro reveals that while GPUs offer superior initial generation speeds, they quickly overheat and throttle. Apple's Neural Engine, though slower to start, maintains a more consis…
-
MLX, LiteRT-LM, and CoreML benchmarked for iPhone LLM performance
A recent benchmark tested four on-device LLM runtimes on an iPhone 17 Pro, comparing decode speed and memory usage. MLX emerged as the fastest for general-purpose models like Qwen 3.5 2B, while LiteRT-LM excelled specif…
-
Google AI Edge Gallery enables on-device agents with MCP support
Google has updated its AI Edge Gallery app to support the Model Context Protocol (MCP) on Android devices, enabling on-device AI agents. This update allows LLMs like Gemma 4 to run entirely locally, enhancing privacy an…