Instructions to use LocalMuseAI/mlx-flux2-klein-4b-aio-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use LocalMuseAI/mlx-flux2-klein-4b-aio-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download LocalMuseAI/mlx-flux2-klein-4b-aio-4bit --local-dir mlx-flux2-klein-4b-aio-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download validation/reference.json from LocalMuseAI/mlx-flux2-klein-4b-aio-4bit: direct link, hf CLI and curl.
- Browser
- Download file 864 Bytes
-
https://huggingface.co/LocalMuseAI/mlx-flux2-klein-4b-aio-4bit/resolve/main/validation/reference.json
- Command line
-
hf download hf://LocalMuseAI/mlx-flux2-klein-4b-aio-4bit/validation/reference.json
-
curl -L -o reference.json https://huggingface.co/LocalMuseAI/mlx-flux2-klein-4b-aio-4bit/resolve/main/validation/reference.json
864 Bytes
| { | |
| "torch": "2.14.1", | |
| "diffusers": "0.40.0", | |
| "transformers": "5.18.0", | |
| "probe": "256x256, sigma 1, seed 1729", | |
| "tokenizerMatches": true, | |
| "encoderBF16VsSwiftInt4": { | |
| "relativeL2": 0.10351864565645792, | |
| "cosine": 0.9951142753409989, | |
| "maximumAbsoluteError": 576.0 | |
| }, | |
| "transformerBF16VsSwiftInt4": { | |
| "relativeL2": 0.11453497637786403, | |
| "cosine": 0.9934259424625762, | |
| "maximumAbsoluteError": 1.0634765625 | |
| }, | |
| "transformerDequantizedVsSwiftInt4": { | |
| "relativeL2": 0.009665547767124439, | |
| "cosine": 0.9999533280974499, | |
| "maximumAbsoluteError": 0.099609375 | |
| }, | |
| "vaeRestoredFP32VsSwiftFP32": { | |
| "relativeL2": 2.549132232262252e-06, | |
| "cosine": 0.9999999999967524, | |
| "maximumAbsoluteError": 3.039836883544922e-06 | |
| }, | |
| "vaeBatchNormPreservedExactly": true, | |
| "elapsedSeconds": 135.06487279199973, | |
| "passed": true | |
| } | |