Instructions to use baa-ai/GLM-5-SWAN-5bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use baa-ai/GLM-5-SWAN-5bit-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-5-SWAN-5bit-MLX baa-ai/GLM-5-SWAN-5bit-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Commit History
Fix: normalise line endings (CR removal) in README 0ed8fe7 verified
Upload README.md with huggingface_hub c27d46c verified
Upload README.md with huggingface_hub 9052236 verified
Update model card: remove MINT/SWAN branding, optimised by baa.ai 25ebac1 verified
Update model card: use generic language for allocation method 93b47f4 verified
Update model card: add MINT-UI link and custom quantization guide c404f66 verified
Update base_model format to include relation: quantized 9fe1d68 verified
Add model card with metrics and usage fa80baa verified
Add SWAN mixed-precision quantized model (5.40 avg bits) 8bcfc1c verified
Trevor Kennedy commited on
Upload README.md with huggingface_hub 4e08bf6 verified
Trevor Kennedy commited on
initial commit dae7811 verified
Trevor Kennedy commited on