FLUX.2 klein 4B (MLX 8-bit)

Pre-quantized MLX weights in the mflux format for faster local loading.

Usage (mflux)

uv tool install --upgrade mflux

mflux-generate-flux2   --model AITRADER/FLUX2-klein-4B-mlx-8bit   --base-model flux2-klein-4b   --prompt "A puffin standing on a cliff"   --width 1024   --height 1024   --steps 50   --guidance 3.5 \
  --seed 42   --output image.png

Notes

This is not an official Black Forest Labs release; it is a convenience repackage for MLX.
For the original model, see black-forest-labs/FLUX.2-klein-4B.

Downloads last month: -

MLX

Hardware compatibility

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AITRADER/FLUX2-klein-4B-mlx-8bit

Base model

black-forest-labs/FLUX.2-klein-4B

Finetuned

(39)

this model