Instructions to use notapalindrome/ltx25-mlx-ditq8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use notapalindrome/ltx25-mlx-ditq8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir ltx25-mlx-ditq8 notapalindrome/ltx25-mlx-ditq8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
notapalindrome/ltx25-mlx-ditq8
Q8 DiT overlay for LTX-2.5 Distilled on Apple Silicon.
Contains transformer-distilled.safetensors (Q8). Pair with the full pack notapalindrome/ltx25-mlx (VAE, Gemma 4, audio, upscalers). Same layout idea as mlx-community/ltx-2.5-mlx-ditq8.
Used by LTX Video Generator as ltx25_distilled_ditq8 (shadow overlay into the base pack).
Derivatives of Lightricks/LTX-2.5 โ see LICENSE.md.
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for notapalindrome/ltx25-mlx-ditq8
Base model
Lightricks/LTX-2.5