--- base_model: google/embeddinggemma-2 library_name: mlx license: apache-2.0 pipeline_tag: feature-extraction tags: - mlx - embedding - feature-extraction - sentence-similarity - image-feature-extraction --- # enconvo/embeddinggemma-2-mlx [EmbeddingGemma 2](https://huggingface.co/google/embeddinggemma-2) by Google for MLX, as Enconvo's Local Embeddings runs it on the Mac: text and image encoders, 768-dimensional normalized vectors. Built from [`mlx-community/embeddinggemma-2-bf16`](https://huggingface.co/mlx-community/embeddinggemma-2-bf16/tree/1a4ffddb7905d3f63486748deabe091a01fb6201) (revision `1a4ffddb`, converted from Google's revision `914f7f89`): - The audio encoder is removed (`audio_config: null`). - The token embedding table (`language_model.embed_tokens`) is stored in 8 bits (affine, group size 64): it is only looked up, so this costs no speed. - Every other weight is bf16, unchanged. Keep activations in bf16. `config.json` records the quantization of that one module, in mlx-lm's layout. Checked against the source on a fixed probe set (16 texts, 8 images at soft-token budgets 70, 280): minimum cosine 0.999761 for text and 0.999757 for images. Use the task prefixes in `config_sentence_transformers.json` (`task: search result | query: ` for queries, `title: none | text: ` for documents). An image is embedded as ` image tokens `. Licence: Apache 2.0, see `LICENSE` and `NOTICE`.