Instructions to use unsloth/Z-Image-Turbo-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-Turbo-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-Turbo-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-Turbo-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-Turbo-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-Turbo-GGUF", max_seq_length=2048, )
GGUFs updated for higher quality!
#2
pinned
by danielhanchen - opened
Hey guys, like Qwen-Image-2512, we updated more variants of Z-Image-Turbo for higher quality results by emphasizing more important layers.
You will need to redownload them for it take effect. Let us know if you see any improvements! :)
danielhanchen pinned discussion
Thank you so much danielhanchen.
I don't study these image gen models - any suggestion what quants to use/avoid?
Been loving your GGUFs! Been massively impressed by the Qwen IQ4 version. Any chance for IQ versions of Z-Image GGUFs?