Google DeepMind's EmbeddingGemma 2 is now available on Ollama

oollama10/6/2026, 14:59:30

EmbeddingGemma 2 is now available on Ollama, bringing Google DeepMind's multimodal open embedding model to consumer devices. Users can pull the model locally with ollama pull embeddinggemma-2.

According to Google DeepMind, EmbeddingGemma 2 is designed for on-device embeddings and unifies code, images, audio, and video alongside text in a shared space.

#embeddinggemma-2 #ollama #google-deepmind #multimodal

View original post ↗

Previous articleAi2 releases technical report on supercharging Olmo-core for MoE training Next articleWHOAFRO uses Google Earth AI agent prototype to map Ebola risk in DRC

Related AI news

Reflection introduces Beam open agentic model with 501B parameters

Reflection announced Beam, an open agentic AI model with 501B total parameters and 23B active parameters, scheduled to release full weights this month. Ollama also stated that more US models are coming to its platform.

oollama•10/5/2026, 12:54:58•

#reflection #beam #ollama #open-source-ai

Ollama lists Nimble, Tev1 4b, and Tev1 0.8b for /v1/systemone

Three models are now available on Ollama for /v1/systemone: Nimble, Tev1 4b, and Tev1 0.8b, each with an Ollama library page.

oollama•9/29/2026, 21:33:22•

#ollama #tev1 #nimble #systemone

Ollama now runs Jev-like decision models locally, including Nimble

Ollama says Jev-like decision models now run entirely on a local machine. Nimble can be installed with ollama pull nimble and used through a new local /v1/systemone API.

oollama•9/29/2026, 21:32:08•

#ollama #nimble #decision-models #local-inference

Google DeepMind introduces EmbeddingGemma 2 for on-device multimodal embeddings

Google DeepMind has introduced EmbeddingGemma 2, its first natively multimodal open model for on-device embeddings that unifies text, code, images, audio, and video in a shared space.

GGoogle DeepMind•10/6/2026, 09:26:32•

#google-deepmind #embeddinggemma-2 #multimodal #embeddings

Google DeepMind releases 740M EmbeddingGemma 2 under Apache 2.0 license

EmbeddingGemma 2 features 740 million parameters and is published under an Apache 2.0 license, providing multimodal search and local retrieval-augmented generation capabilities on device.

GGoogle DeepMind•10/6/2026, 09:33:57•

#embeddinggemma-2 #google-deepmind #apache-2.0 #multimodal-embeddings

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy