Google launches EmbeddingGemma 2: on-device multimodal embeddings with +14% on MTEB Code
DynamicWebPaige · x · 2026-10-07
Google released EmbeddingGemma 2, an open Apache 2.0 embeddings model for on-device use covering code, image, video, audio and text. Key specs: modular footprint from 270M (text/code) up to 740M full multimodal, Matryoshka embeddings truncatable to 128d for 6x storage savings, and +14% on MTEB Code vs v1. Demos and a developer guide are live on Hugging Face.
More from Models
- Paradigm releases tech report for Violetto, a 1B model trained from scratch for math — tensorqt · 2026-10-07
- Mistral's Le Chonk tops blind human code review among open models, second only to Opus 5 — qtnx_ · 2026-10-07
- DeepSeek V4.1 Flash hits 72.9% on ARC-AGI-2 at $0.13/task, costing 250% more — teortaxesTex · 2026-10-07
- Mistral claims Large 4 is one of the world's strongest AI models for cybersecurity — scaling01 · 2026-10-07
- Mistral Large 4 solves 18 of 19 CTF challenges in official speedrun with tool calls — MistralAI · 2026-10-07
- Community poll tiers AI labs: Anthropic and OpenAI frontier, Mistral and Amazon judged 3 generations behind — NathanpmYoung · 2026-10-07