Google ships EmbeddingGemma 2: 740M multimodal embeddings under Apache 2.0
GlennCameronjr · x · 2026-10-07
Google's Gemma team released EmbeddingGemma 2, a lightweight multimodal embedding model that maps text, code, images, video, and audio into a single unified embedding space. Key specs: 740M parameters with modular encoders, flexible 768–128 dimension sizes via Matryoshka Representation Learning, an 8K context window (4x the text-only predecessor), on-device optimization, and a commercially permissive Apache 2.0 license.
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