Z-Image-Turbo Nunchaku Lite NVFP4 r32

Diffusers-loadable conversion of:

Base model: Tongyi-MAI/Z-Image-Turbo
Source repo: nunchaku-ai/nunchaku-z-image-turbo
Source checkpoint: svdq-fp4_r32-z-image-turbo.safetensors

The transformer uses quant_method: nunchaku_lite, NVFP4 SVDQ, group size 16, rank 32, and 238 quantized targets. Packed fused QKV and SwiGLU projections are split in logical layout into the stock Z-Image graph. The Qwen3 text encoder is packaged with BitsAndBytes 4-bit NF4.

Benchmark

Checkpoint	Latency	Max VRAM
Converted Diffusers Nunchaku Lite NVFP4 r32 + BNB4 Qwen3	1.68 s (stdev 0.00 s)	12.11 GiB
Original Nunchaku NVFP4 r32 + BF16 Qwen3	1.31 s (stdev 0.00 s)	16.57 GiB

RTX 5090, 1024×1024, 9 scheduler steps (8 DiT forwards), guidance scale 0, seed 42, one warmup and three measured runs. VRAM is peak total device usage sampled through nvidia-smi. The native row uses the base model's BF16 Qwen3 encoder.

Output Comparison

Both images use the same prompt, seed, scheduler, resolution, and step count. Same-precision pixel MAE is 13.37 and RMSE is 24.12.

Run

Requires the Hugging Face kernels package and an NVIDIA Blackwell GPU.

import torch
from diffusers import ZImagePipeline

pipe = ZImagePipeline.from_pretrained(
    "lite-infer/z-image-turbo-nunchaku-lite-nvfp4_r32-bnb4-text-encoder",
    torch_dtype=torch.bfloat16,
).to("cuda")

image = pipe(
    prompt='A cinematic portrait of a red fox in a misty forest at sunrise, detailed fur, volumetric light',
    height=1024,
    width=1024,
    num_inference_steps=9,
    guidance_scale=0.0,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]
image.save("output.png")