Instructions to use mlx-community/gemma-4-12B-it-assistant-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/gemma-4-12B-it-assistant-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-12B-it-assistant-4bit mlx-community/gemma-4-12B-it-assistant-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from mlx-community/gemma-4-12B-it-assistant-4bit: direct link, hf CLI and curl.
- Browser
- Download file 32.2 MB
-
https://huggingface.co/mlx-community/gemma-4-12B-it-assistant-4bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://mlx-community/gemma-4-12B-it-assistant-4bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/mlx-community/gemma-4-12B-it-assistant-4bit/resolve/main/tokenizer.json
32.2 MB
- Xet hash:
- 18dbcc705c7f507f8d37bb28c5b58325e55304bfe8ff3cd8f6e44f5e90a436d3
- Size of remote file:
- 32.2 MB
- SHA256:
- c001d9ada50af662c94f5ab17ec7e09f6438d1bec8246c47fee6510693d8de35
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.