| --- |
| license: other |
| license_name: flux-non-commercial-license |
| license_link: https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B/blob/main/LICENSE.md |
| extra_gated_prompt: "Access is for non-commercial use under the FLUX Non-Commercial License and Black Forest Labs Acceptable Use Policy. This repository is a quantized derivative of a gated Black Forest Labs FLUX.2 Klein 9B model." |
| extra_gated_fields: |
| I agree to use this model for non-commercial use only: checkbox |
| I agree to follow the FLUX Non-Commercial License: checkbox |
| I acknowledge the Black Forest Labs Acceptable Use Policy: checkbox |
| base_model: black-forest-labs/FLUX.2-klein-base-9B |
| pipeline_tag: text-to-image |
| library_name: mlx-gen |
| tags: |
| - mlx |
| - mlx-gen |
| - mflux |
| - apple-silicon |
| - 8-bit |
| - flux |
| - flux2 |
| --- |
| # flux.2-klein-base-9b-8bit |
|
|
| This repository contains MLX-Gen saved weights for `black-forest-labs/FLUX.2-klein-base-9B`. The checkpoint is designed for local Apple Silicon inference with [`mlx-gen`](https://github.com/lpalbou/mlx-gen). |
|
|
| It uses the mflux/MLX saved-weight layout and MLX quantization tensors. It is not a Diffusers or Transformers `from_pretrained()` checkpoint. |
|
|
| ## Source Model |
|
|
| Original model: [`black-forest-labs/FLUX.2-klein-base-9B`](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B). |
|
|
| ## License and Access |
|
|
| This checkpoint is a quantized derivative of a gated Black Forest Labs FLUX.2 Klein 9B source model. The source model is distributed under the [FLUX Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B/blob/main/LICENSE.md). |
|
|
| Host this derivative as a gated Hugging Face repository and require users to accept the same non-commercial license terms and [Black Forest Labs Acceptable Use Policy](https://bfl.ai/legal/usage-policy) before accessing the files. |
|
|
| ## Quantization |
|
|
| This is an MLX q8 checkpoint. Quantizable modules are saved at 8-bit where the model layout supports MLX quantization; VAE weights and non-quantizable layers remain BF16. |
|
|
| ## Compatibility |
|
|
| Requires `mlx-gen >= 0.18.2`. |
|
|
| Generated with `mlx-gen 0.18.2`. |
|
|
| Use the `mlxgen` command and Python import path for new MLX-Gen projects. |
|
|
| ## Usage |
|
|
| ```bash |
| python -m pip install -U mlx-gen |
| |
| mlxgen download --model AbstractFramework/flux.2-klein-base-9b-8bit |
| |
| mlxgen generate \ |
| --model AbstractFramework/flux.2-klein-base-9b-8bit \ |
| --prompt "Your prompt here" \ |
| --steps 20 \ |
| --seed 42 \ |
| --output image.png |
| ``` |
|
|
| ## Attribution |
|
|
| MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. This model card is generated by MLX-Gen so derived checkpoints keep that attribution visible. |
|
|
| Quantized and contributed by [@lpalbou](https://huggingface.co/lpalbou). |
|
|
