Instructions to use lpalbou/flux2-klein-4b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use lpalbou/flux2-klein-4b-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir flux2-klein-4b-4bit lpalbou/flux2-klein-4b-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
lpalbou/flux2-klein-4b-4bit
This repository contains the 4-bit quantized weights for black-forest-labs/FLUX.2-klein-4B, generated using the mflux framework.
Usage
You can run this model locally on Apple Silicon using mflux:
pip install mflux
mflux-generate-flux2 --model mlx-community/flux2-klein-4b-4bit --prompt "A beautiful pencil sketch of a landscape" --steps 4 --seed 42
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for lpalbou/flux2-klein-4b-4bit
Base model
black-forest-labs/FLUX.2-klein-4B