Instructions to use andrevp/Z-Image-Turbo-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use andrevp/Z-Image-Turbo-MLX-2bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download andrevp/Z-Image-Turbo-MLX-2bit --local-dir Z-Image-Turbo-MLX-2bit
- Diffusers
How to use andrevp/Z-Image-Turbo-MLX-2bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("andrevp/Z-Image-Turbo-MLX-2bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download quantize_config.json from andrevp/Z-Image-Turbo-MLX-2bit: direct link, hf CLI and curl.
- Browser
- Download file 107 Bytes
-
https://huggingface.co/andrevp/Z-Image-Turbo-MLX-2bit/resolve/main/quantize_config.json
- Command line
-
hf download hf://andrevp/Z-Image-Turbo-MLX-2bit/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/andrevp/Z-Image-Turbo-MLX-2bit/resolve/main/quantize_config.json
107 Bytes
| { | |
| "quantization": { | |
| "bits": 2, | |
| "group_size": 64, | |
| "skip_components": [ | |
| "vae" | |
| ] | |
| } | |
| } |