Instructions to use unsloth/Z-Image-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Studio
How to use unsloth/Z-Image-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Z-Image-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for unsloth/Z-Image-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for unsloth/Z-Image-GGUF to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="unsloth/Z-Image-GGUF", max_seq_length=2048, )
Making new gguf models from FP32 version .
#1
by Dante405 - opened
The problem is recently a fp32 version of Z image base was leaked which is stored at :
https://huggingface.co/notaneimu/z-image-base-comfy-fp32
https://huggingface.co/Hellrunner/z_image_fp32
If possible can unsloth create new gguf models from the fp32 version it is improvement over there bf16 version release on there Tongyi's official Z image base repo.