At Google I/O, Google introduced a new Coral board that enables running the Gemma 3 language model locally. This represents a major advancement for Edge AI applications, allowing natural language processing directly on-device without the need for a cloud connection.
Liquid AI introduces LFM2.5-8B-A1B, an 8-billion parameter language model with a hybrid MoE architecture, designed specifically for smartphones, laptops, and robots. Featuring a 128K context window, this is a major step forward in bringing high-performance AI directly to edge devices.
Marlin-2B is an open-source VLM with only 2 billion parameters that offers powerful video analysis capabilities, competing directly with larger models like Gemini-2.5-flash.
