Instructions to use t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.5-2B-MLX-MTP-bf16 t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download video_preprocessor_config.json from t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16: direct link, hf CLI and curl.
- Browser
- Download file 385 Bytes
-
https://huggingface.co/t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16/resolve/eb14195eea53195dc00d934d1eb691cde5e243e1/video_preprocessor_config.json
- Command line
-
hf download hf://t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16@eb14195eea53195dc00d934d1eb691cde5e243e1/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/t0rr3sp3dr0/Qwen3.5-2B-MLX-MTP-bf16/resolve/eb14195eea53195dc00d934d1eb691cde5e243e1/video_preprocessor_config.json
385 Bytes
| { | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } |