Instructions to use Neo39982/Behemoth-R1-123B-v2-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Neo39982/Behemoth-R1-123B-v2-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Behemoth-R1-123B-v2-mlx-4Bit Neo39982/Behemoth-R1-123B-v2-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download model-00002-of-00014.safetensors from Neo39982/Behemoth-R1-123B-v2-mlx-4Bit: direct link, hf CLI and curl.
- Browser
- Download file 5.25 GB
-
https://huggingface.co/Neo39982/Behemoth-R1-123B-v2-mlx-4Bit/resolve/main/model-00002-of-00014.safetensors
- Command line
-
hf download hf://Neo39982/Behemoth-R1-123B-v2-mlx-4Bit/model-00002-of-00014.safetensors
-
curl -L -o model-00002-of-00014.safetensors https://huggingface.co/Neo39982/Behemoth-R1-123B-v2-mlx-4Bit/resolve/main/model-00002-of-00014.safetensors
5.25 GB
- Xet hash:
- 3b8d8f4689f8fc56a91128e46185e524a487a9106237ef83392d7f7d286ea1be
- Size of remote file:
- 5.25 GB
- SHA256:
- cd0746992a2e99acd0eef9edbf9922d530f3de415230638d95ad4ef431893107
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.