Any-to-Any
MLX
Safetensors
English
gemma4_unified
2-bit
heretic
uncensored
decensored
abliterated
4-bit precision
Instructions to use zecanard/gemma-4-12b-it-uncensored-heretic-MLX-2bit-mixed_2_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use zecanard/gemma-4-12b-it-uncensored-heretic-MLX-2bit-mixed_2_6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gemma-4-12b-it-uncensored-heretic-MLX-2bit-mixed_2_6 zecanard/gemma-4-12b-it-uncensored-heretic-MLX-2bit-mixed_2_6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- e96a17bb638d7e5c417d4c2abf3cdb5af7a97b50605a250f2f6d84c29b46d1d9
- Size of remote file:
- 32.2 MB
- SHA256:
- a2619fe11b50dbed06ac443c51d757b354d0b62d64baa514404d4e84e6713519
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.