Downloads · 30 days
12
13% of all-time downloads
Onyx-Z-Image-Turbo-4bit
wabibito/Onyx-Z-Image-Turbo-4bit
Onyx-Z-Image-Turbo-4bit is a text-to-image model from wabibito. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
A 4-bit MLX quantization of the official Tongyi-MAI/Z-Image-Turbo, built for on-device inference in the Onyx app with a documented, reproducible pipeline.
All-time downloads
95
Public
Parameters
963M
6.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.5 GB · 100%
Parameter types
How the weights are stored.
U32769M · 80%
Base models
Model card
From the Hugging Face model README
Onyx Z Image Turbo — 4-bit MLX
A 4-bit MLX quantization of the official Tongyi-MAI/Z-Image-Turbo, built for
on-device inference in the Onyx app with a documented, reproducible pipeline.
- Source: official
Tongyi-MAI/Z-Image-Turbo(diffusers), quantized in-house. - Quantization: 4-bit, group 64, MLX. Only transformer + text-encoder Linear leaves are quantized;
norms/embeddings/convs and the whole VAE stay fp16. Components:
transformer/,text_encoder/(Qwen3),vae/(16-ch FLUX-family),tokenizer/,scheduler/. - Inference: ~8 steps, CFG off (distilled).
- Verified: reloaded through the Onyx engine and render-checked before publish.
Quantized derivative for efficient on-device use; all credit for the model to Tongyi-MAI (Alibaba).
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Created
- Jul 9, 2026
- Updated
- Jul 28, 2026