← model directory

cloudflare

google/embeddinggemma-300m

cloudflare/google/embeddinggemma-300m

↓ runs free on your own hardware

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

specs & pricing
Type
embeddings
Provider
cloudflare
Model ID
cloudflare/google/embeddinggemma-300m
Self-hostable
Yes — runs on your own GPU

Listed in the directory for discovery. embeddingsmodels aren't callable through the chat gateway yet — image and video models can run on your own nodes today.