MLX
Safetensors
glm4_moe_lite_mtp
speculative-decoding
multi-token-prediction
drafter
4-bit precision
Instructions to use samithaj/GLM-4.7-Flash-MTP-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use samithaj/GLM-4.7-Flash-MTP-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-4.7-Flash-MTP-4bit samithaj/GLM-4.7-Flash-MTP-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio