Google launches EmbeddingGemma 2, first open multimodal on-device embedding model
NVIDIAAI · x · 2026-10-07
Google DeepMind has released EmbeddingGemma 2, described as its first natively multimodal open model for on-device embeddings.
Beyond text, it unifies code, images, audio, and video in a shared vector space. NVIDIA's AI account publicly congratulated the team, underscoring the significance of an open, on-device multimodal embedding model for retrieval and search workloads.
More from Multimodal
- LichtFeld Densification plugin cuts runtime from 85.5s to 16.7s on same GPU — janusch_patas · 2026-10-07
- Nano Banana 2.1 ships with higher-quality images, bug fixes, and lower prices — OfficialLoganK · 2026-10-07
- OmniReasoning: audio-visual joint reasoning benchmark lifts Qwen3-Omni by 12.8 points — _akhaliq · 2026-10-07
- Seedance 2.5 generates a 30-second Paris Halloween heist, upscaled 480p to 1080p — LudovicCreator · 2026-10-07
- Kling 4.0 Flash short: robot promises human cruelty is gone — but never says how — LudovicCreator · 2026-10-07
- MiniMax H3 Ecosystem Daily: ComfyUI 0.39 Fixes VAE, CivitAI Launches Film Contest — optimisticalish · 2026-10-07