Instructions to use Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit --local-dir GLM-4.5-Iceblink-106B-A12B-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Wwayu/GLM-4.5-Iceblink-106B-A12B-mlx-4Bit/resolve/main/tokenizer.json
20 MB
- Xet hash:
- 6cb1d3ff8655d0ce955a565b7fa0a50a259c3f1a5485aa1aa268d0bbfe07bc95
- Size of remote file:
- 20 MB
- SHA256:
- bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.