uqer1244/MLX_z-image
MLX version of z-image model
Implements Z-Image-Turbo for Apple Silicon with 4-bit quantization and optimizations including fused QKV projections, hardware-accelerated Flash Attention, and cached rotary embeddings to minimize memory bandwidth bottlenecks. The pipeline integrates a native MLX transformer with PyTorch-based text encoder and VAE components, supporting LoRA adapters and ComfyUI nodes for local image generation on Mac devices.
Stars
46
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/uqer1244/MLX_z-image"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
astriaai/imagine
A GUI for Flux image generation
Pikselkroken/pixlstash
PixlStash is a Python-based image management and analysis web app leveraging AI tools for...
airesearch-official/Z-Image-Turbo-Windows
One-click Windows installer for Z-Image Turbo AI image generation. Optimized for low-VRAM GPUs...
MutantSparrow/JustRayzist
A lightweight CUDA-based local inference platform built around Z-Image Turbo by Tongyi
SamuelTallet/ZPix
A local AI image generator powered by the Z-Image Turbo model