Instructions to use brainworkup/granite-4.1-3b-oQ8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use brainworkup/granite-4.1-3b-oQ8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download brainworkup/granite-4.1-3b-oQ8 --local-dir granite-4.1-3b-oQ8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from brainworkup/granite-4.1-3b-oQ8: direct link, hf CLI and curl.
- Browser
- Download file 7.15 MB
-
https://huggingface.co/brainworkup/granite-4.1-3b-oQ8/resolve/main/tokenizer.json
- Command line
-
hf download hf://brainworkup/granite-4.1-3b-oQ8/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/brainworkup/granite-4.1-3b-oQ8/resolve/main/tokenizer.json
7.15 MB
File too large to display, you can check the raw version instead.