fromInfoQ3 weeks agoGemma 3n Introduces Novel Techniques for Enhanced Mobile AI InferenceGemma 3n employs Per-Layer Embeddings (PLE) to optimize RAM usage by loading core transformer weights into VRAM while keeping other parameters on the CPU.Mobile UX
Artificial intelligencefromTechCrunch2 months agoThe latest Google Gemma AI model can run on phones | TechCrunchGemma 3n is a versatile AI model focused on offline efficiency and privacy for various devices.