zimgturbo weights (int8)

int8-quantized Z-Image-Turbo for the zimgturbo engine on Apple Silicon. Derived from Tongyi-MAI/Z-Image-Turbo.

uvx zimgturbo setup            # pulls this bundle
uvx zimgturbo "a cat on a windowsill" -o cat.png

Contents: weights.bin/weights.idx (int8 DiT), text_encoder_int8.safetensors (int8 Qwen3), vae.safetensors+vae_config.json (fp16 VAE), text_encoder/config.json, tokenizer/.

Downloads last month

-

Downloads are not tracked for this model. How to track
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for yunfengwang/zimgturbo

Finetuned
(141)
this model