Instructions to use SceneWorks/flux2-klein-9b-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/flux2-klein-9b-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download SceneWorks/flux2-klein-9b-mlx --local-dir flux2-klein-9b-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
sc-22760: drop the false quantization marker from q4/q8 text_encoder/config.json
Verified signatureThe q4/q8 tiers ship the Qwen3 text encoder dense (399 BF16 tensors, no scales/biases); only config.json claimed Q4/Q8. The encoder contract refuses the config/surface mismatch, so no native load of these tiers was possible. Weights unchanged.1902693
-
Add missing scheduler/scheduler_config.json to q4/q8/bf16 tiers (fixes false-incomplete gate, GH SceneWorks/SceneWorks#1858)
Verified signatureacf05e8
-
sc-8711: bf16/model_index.json
Verified signature1d36c68 -
sc-8711: bf16/tokenizer
Verified signatured3a7bc7 -
sc-8711: bf16/vae
Verified signature43a43e9 -
sc-8711: bf16/text_encoder
Verified signature1d4c742 -
sc-8711: bf16/transformer
Verified signature9c48f01 -
sc-8711: q8
Verified signaturecf5ff6d -
sc-8711: q4
Verified signatureda873dc -
Upload LICENSE.md with huggingface_hub
Verified signature3598881 -
Upload README.md with huggingface_hub
Verified signaturef2f8f41 -
initial commit
Verified signaturef02bf60