Instructions to use mzbac/flux1.kontext.4bit.mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mzbac/flux1.kontext.4bit.mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir flux1.kontext.4bit.mlx mzbac/flux1.kontext.4bit.mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
flux.swift.cli
#1
by Pall13 - opened
βHi! I downloaded your quantized FLUX.1-Kontext model and tried to use it with flux.swift.cli as described in the README, but it keeps downloading the full model instead of using the local quantized one. Is there a specific version of flux.swift.cli or a special flag needed to load it correctly?β
Error: Unknown option '--load-quantized-path'
Usage: flux
See 'flux --help' for more information.