AI News/Wire summary
EmbeddingGemma 2 adds on-device multimodal embeddings for text, images, audio and video
Key points
- Open model under Apache 2.0 license, 740 million parameters, built on the Gemma 4 architecture
- Code benchmark score rises from 68.76 to 78.68 on MTEB Code, per Google's reported results
- Context window of 8K tokens, up from 4x smaller in the first EmbeddingGemma
- Weights available on Hugging Face and Kaggle; Gemini Enterprise Agent Platform availability is coming soon
Why it matters for marketers: Content and app teams can build offline search over media libraries and video or audio clips without sending data to the cloud.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
Google DeepMind: EmbeddingGemma 2: an open, lightweight multimodal embedding model
Related on Z Media
- Meta releases Muse Spark Open, runnable on two Apple Mac Studiosvia The Verge, 7 hr ago
- Nvidia opens up Super VL, a model for always-on enterprise agentsOur brief, via The Decoder, 9 hr ago
- Meta releases Muse Spark Open, an open-weight multimodal coding modelvia Hugging Face, yesterday
- FLUX.3 Image Klein lands in Diffusers with bounding-box layout controlvia Hugging Face, yesterday
- openKylin outlines AI-era Linux vision at Open Source Summit Europevia MarkTechPost, 12 hr ago
- Fish Audio releases Drama 3 open-weight text-to-speech modelvia MarkTechPost, yesterday