Instructions to use SceneWorks/ltx-2.3-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SceneWorks/ltx-2.3-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download SceneWorks/ltx-2.3-mlx --local-dir ltx-2.3-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download q8/split_model.json from SceneWorks/ltx-2.3-mlx: direct link, hf CLI and curl.
- Browser
- Download file 435 Bytes
-
https://huggingface.co/SceneWorks/ltx-2.3-mlx/resolve/main/q8/split_model.json
- Command line
-
hf download hf://SceneWorks/ltx-2.3-mlx/q8/split_model.json
-
curl -L -o split_model.json https://huggingface.co/SceneWorks/ltx-2.3-mlx/resolve/main/q8/split_model.json
435 Bytes
| { | |
| "format": "split", | |
| "model_version": "2.3.0", | |
| "components": [ | |
| "transformer", | |
| "connector", | |
| "vae_decoder", | |
| "vae_encoder", | |
| "audio_vae", | |
| "vocoder", | |
| "upsampler", | |
| "spatial_upscaler_x2_v1_1", | |
| "spatial_upscaler_x1_5_v1_0", | |
| "temporal_upscaler_x2_v1_0" | |
| ], | |
| "source": "Lightricks/LTX-2.3", | |
| "variant": "distilled", | |
| "quantized": true, | |
| "quantization_bits": 8, | |
| "quantization_group_size": 64 | |
| } |