FLUX.1-Kontext 8-bit Quantized for MLX

This is an 8-bit quantized version of the FLUX.1-Kontext-dev model optimized for use with MLX and flux.swift. The model size has been reduced from ~24GB to 17GB while maintaining excellent image-to-image generation quality.

Quantized using flux.swift, a Swift implementation of FLUX models for Apple Silicon.

Model Details

  • Quantization: 8-bit with group size 128
  • Total Size: 17GB
  • Original Model: black-forest-labs/FLUX.1-Kontext-dev
  • Framework: MLX (Metal Performance Shaders)
  • Components: Transformer, VAE, CLIP text encoder, T5 text encoder

Usage

This model requires the flux.swift implementation. Please refer to the repository for installation and usage instructions.

Quick Start

# Load and use the quantized model for image-to-image generation
flux.swift.cli \
  --load-quantized-path /path/to/this/model \
  --hf-token YOUR_HF_TOKEN \
  --init-image-path /path/to/input/image.png \
  --prompt "Your transformation prompt here" \
  --output output.png

Recommended Parameters

  • Steps: 30
  • Guidance Scale: 3.5
  • Authentication: Requires Hugging Face token
  • Input: Requires --init-image-path for image-to-image generation

Example with Parameters

flux.swift.cli \
  --load-quantized-path /path/to/this/model \
  --hf-token YOUR_HF_TOKEN \
  --init-image-path ./reference.png \
  --prompt "transform this into a watercolor painting with soft pastel tones" \
  --steps 30 \
  --guidance 3.5 \
  --width 512 \
  --height 512 \
  --seed 42 \
  --output watercolor_painting.png

License

This model is a quantized version of FLUX.1-Kontext-dev, which is licensed under the FLUX.1 [dev] Non-Commercial License. Please review the original license terms:

Performance

  • Memory Usage: Reduced from ~24GB to 17GB
  • Quality: Excellent preservation of image-to-image generation quality
  • Platform: Optimized for Apple Silicon Macs

Citation

@misc{flux-kontext,
  author = {Black Forest Labs},
  title = {FLUX.1-Kontext-dev},
  publisher = {Black Forest Labs},
  year = {2024},
  url = {https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev}
}

@software{flux-swift,
  author = {mzbac},
  title = {flux.swift: Swift implementation of FLUX models},
  url = {https://github.com/mzbac/flux.swift},
  year = {2024}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
MLX
Hardware compatibility
Log In to view the estimation

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support