Instructions to use QuantLLM/functiongemma-270m-it-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use QuantLLM/functiongemma-270m-it-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir functiongemma-270m-it-4bit-mlx QuantLLM/functiongemma-270m-it-4bit-mlx
- Transformers
How to use QuantLLM/functiongemma-270m-it-4bit-mlx with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("QuantLLM/functiongemma-270m-it-4bit-mlx", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| # Convert to MLX | |
| This model was saved in HuggingFace format. | |
| To convert to MLX format on Apple Silicon: | |
| ```bash | |
| pip install mlx-lm | |
| python -m mlx_lm.convert --hf-path ./hub_staging/functiongemma-270m-it-4bit-mlx --mlx-path ./mlx_model | |
| ``` | |