Downloads · 30 days
11
6% of all-time downloads
embeddinggemma-300m-ov
beclab/embeddinggemma-300m-ov
embeddinggemma-300m-ov is a feature extraction model from beclab. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers. The card lists the license as gemma.
OpenVINO IR (FP32) export of google/embeddinggemma-300m, packaged for IREmbeddingServer inference (MODELID=embeddinggemma-300m-ov).
All-time downloads
189
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.2 GB · 95%
At a glance
- Task
- Feature Extraction
- Library
- sentence-transformers
- License
- gemma
- Model type
- gemma3_text
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- 45cf6694
Base models
Model card
From the Hugging Face model README
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.
- Task
- Feature Extraction
- Library
- sentence-transformers
- Type
- gemma3_text
- License
- gemma
- Languages
- en, multilingual
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026