EmbeddingGemma 2 Launches: First Native Multimodal Embeddings, Apache 2.0, +14% MTEB Code
_philschmid · x · 2026-10-07
EmbeddingGemma 2 is out—Google's first native multimodal embedding model, built on Gemma 4 under Apache 2.0. It embeds 100+ languages, code, images, audio and video into one vector, supports 8,192 context, comes in 740M/440M/570M/270M variants, gains +14% on MTEB Code, and supports Matryoshka dimensions from 768 down to 128. Available via Sentence Transformers and LiteRT-LM.
More from Models
- Two Labs, One Race: Anthropic vs OpenAI Frontier Model Release Timeline, 2023–2026 — Medical-Sky7620 · 2026-10-07
- Claude was given robot skin — Opus was curious but anxious about hooking up — repligate · 2026-10-07
- Gemini 2.5 Pro retiring October 20, 2026, users say goodbye — hargup13 · 2026-10-07
- OpenAI shipped Decisions API just two weeks after first prototype — stevenheidel · 2026-10-07
- User marvels as ChatGPT shows humanlike academic skills — dioscuri · 2026-10-07
- Why Hybrid Models May Scale Better Downstream: The Inductive-Bias Argument — kalomaze · 2026-10-07