Feature Extraction
MLX
Safetensors
qwen3_5
quantized
8-bit precision
apple-silicon
uembed
embeddings
text-embedding
Instructions to use majentik/UEmbed-2B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/UEmbed-2B-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download majentik/UEmbed-2B-MLX-8bit --local-dir UEmbed-2B-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from majentik/UEmbed-2B-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/majentik/UEmbed-2B-MLX-8bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://majentik/UEmbed-2B-MLX-8bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/majentik/UEmbed-2B-MLX-8bit/resolve/main/tokenizer.json
20 MB
- Xet hash:
- 458bcbf483ed805b4297af928f717e64bd00c633a07be5fae5717cacbd48e2ef
- Size of remote file:
- 20 MB
- SHA256:
- 87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.