MLX Embedding Models
Run text embeddings on your Apple Silicon GPU. Supports any BERT- or RoBERTa-based embedding model, with a curated registry of high-performing models that just work off the shelf.
Get started by installing from PyPI:
pip install mlx-embedding-models
Then get started in a few lines of code:
from mlx_embedding_models.embedding import EmbeddingModel
model = EmbeddingModel.from_registry("bge-small")
texts = [
"isn't it nice to be inside such a fancy computer",
"the horse raced past the barn fell"
]
embs = model.encode(texts)
print(embs.shape)
# 2, 384
1 maintainer
Metadata
1 maintainer
Release files for mlx-embedding-models 0.0.11
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mlx_embedding_models-0.0.11.tar.gz | 13.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mlx_embedding_models-0.0.11-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 28.6 kB
Release files / mlx_embedding_models-0.0.11.tar.gz
| Download URL | mlx_embedding_models-0.0.11.tar.gz |
|---|---|
| Size | 13.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9dcb01462736cca9e9014a032f5df2fb58cad6f1a9d6f70e321103cb67cb136c
|
|
BLAKE2b-256 checksum How to use checksums |
a409ff384fc20f602dca2877b823bff15dbec2259edab146bd18992d3e388ebc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.13
|
Release files / mlx_embedding_models-0.0.11-py3-none-any.whl
| Download URL | mlx_embedding_models-0.0.11-py3-none-any.whl |
|---|---|
| Size | 15.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
518c8d02773bf8afadc832e41ae473bd7433d609084b4930f3ce6ee47fbc6a6e
|
|
BLAKE2b-256 checksum How to use checksums |
8e4f5c09805363daa711368c6c3b86d1a24839b2512f3e75406fe4d75cd16f33
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.13
|
