EmbeddingGemma-300M OpenVINO FP32

OpenVINO IR (FP32) export of google/embeddinggemma-300m, packaged for IREmbeddingServer inference (MODEL_ID=embeddinggemma-300m-ov).

Layout

Path Description
openvino_model.xml / openvino_model.bin Gemma3 backbone IR (~1.2GB FP32)
2_Dense/ / 3_Dense/ Sentence Transformers Dense layers (post-OV matmul)
tokenizer.json Tokenizer
modules.json ST module metadata

IREmbeddingServer

export EMBED_MODEL_DIR="./embeddinggemma-300m-ov"
export MODEL_ID=embeddinggemma-300m-ov
export EMBED_DEVICE=cpu   # or igpu / npu

License

Derived from Google's EmbeddingGemma (Gemma license). See google/embeddinggemma-300m.

Downloads last month
81
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for beclab/embeddinggemma-300m-ov

Finetuned
(264)
this model