GGUF-Org Z-Image GGUF Models

Official GGUF quantized versions of Z-Image Turbo models for low-VRAM deployment (6GB+), optimized for ComfyUI with multiple quantization levels

GGUF

Quantization

Low VRAM

ComfyUI

6GB Compatible

Consumer GPU

Visit Resource

Overview

GGUF-Org provides officially converted GGUF quantized versions of Z-Image Turbo, enabling deployment on consumer-grade GPUs with as low as 6GB VRAM. Supports multiple quantization levels including Q3_K_S, IQ4_NL, and IQ4_XS for different VRAM/quality trade-offs.

Features

Multiple quantization levels: Q3_K_S (6GB), IQ4_NL/IQ4_XS (8GB)
Compatible with ComfyUI via GGUF-Connector or ComfyUI-GGUF extension
Supports various Qwen3 text encoder variants
Memory-mapped file format for efficient loading
Maintains image quality while reducing VRAM requirements by up to 70%
Includes VAE and text encoder models

Installation

Download GGUF files and place in ComfyUI directories:
- Z-Image model → ./ComfyUI/models/diffusion_models
- Qwen3-4B encoder → ./ComfyUI/models/text_encoders
- VAE → ./ComfyUI/models/vae

Usage

Use with ComfyUI GGUF extension or gguf-connector CLI tool. Run 'ggc z1' to select and interact with GGUF models.

Requirements