Technology
EmbeddingGemma 2
StableFollow
01
Recent changes
- Google launches EmbeddingGemma 2: supports multimodal, optimizes on-device performanceGoogle has launched EmbeddingGemma 2, which supports multimodal content, with 740 million parameters, suitable for running on mobile devices, requiring only 191MB of memory.Stable1 sources · 3 evidence2026-10-07 06:41
- Google DeepMind releases EmbeddingGemma 2, a lightweight multimodal embedding model for on-device useGoogle DeepMind has launched EmbeddingGemma 2, an open-source multimodal embedding model with 740 million parameters that unifies text, images, audio, and video in a shared embedding space. Built on Gemma 4 architecture and released under Apache 2.0 license, it supports on-device inference with as little as 191MB RAM for text-only workloads and features an 8K token context window.StableTechnology2 sources · 1 primary · 15 evidence2026-10-07 03:57