Instructions to use SceneWorks/Mage-Flow-Components-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/Mage-Flow-Components-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download SceneWorks/Mage-Flow-Components-mlx --local-dir Mage-Flow-Components-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
sc-15071: regenerate the q4 tier with the 8-bit precision floors
Verified signatureThe previous q4 artifact was packed uniformly at 4 bits, which made the tier render a repeating tiled texture instead of the prompt. norm_out.linear (the output head's adaLN modulation) and the Qwen3-VL LM decoder layers are now packed at 8 bits; everything else is unchanged. q8 and bf16 are untouched.c936de2 -
feat(sc-14980): shared Qwen3-VL TE + Mage-VAE as per-tier MLX artifacts
Verified signature5b6ab82 -
initial commit
Verified signature40feb5c