Downloads · 30 days
42
36% of all-time downloads
lite-infer/krea-2-turbo-nunchaku-lite-nvfp4-r32
krea-2-turbo-nunchaku-lite-nvfp4-r32 is a text-to-image model from lite-infer. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
Diffusers-loadable NVFP4 conversion of krea/Krea-2-Turbo, quantized with diffuse-compressor. It loads with a plain frompretrained call — no runtime graph patches and no extra runtime package.
Downloads · 30 days
42
36% of all-time downloads
All-time downloads
116
Public
Parameters
7.5B
11.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors11.5 GB · 100%
How the weights are stored.
I86.2B · 84%
From the Hugging Face model README
Diffusers-loadable NVFP4 conversion of krea/Krea-2-Turbo, quantized with
diffuse-compressor. It
loads with a plain from_pretrained call — no runtime graph patches and no extra
runtime package.
The transformer uses quant_method: nunchaku_lite, NVFP4 SVDQ with group size
16, rank 32, 256 SVDQ targets and no AWQ W4A16 targets. Eight outer linears (img_in, time/text embedders, time_mod_proj, text_fusion.projector, final_layer.linear) stay
in bf16, and the text_encoder component is BitsAndBytes 4-bit NF4 with bf16
compute. QKV projections are not fused, so this trades some speed for loading
through the stock Diffusers graph. Calibrated on 32 prompts at
8 steps, 1024x1024.
| Checkpoint | Latency | Max VRAM |
|---|---|---|
| This repo — Nunchaku Lite NVFP4 r32 + BNB4 text encoder | 34.06 s (stdev 0.03 s) | 20.34 GiB |
| Nunchaku Lite INT4 r32 + BNB4 text encoder | 60.70 s (stdev 0.04 s) | 19.97 GiB |
NVIDIA RTX PRO 4000 Blackwell, settings as in the Run snippet below, one warmup and three measured runs, everything resident on the GPU with no offload. Latency covers the full pipeline call; VRAM is peak device usage.
There is no dense bf16 row because it does not fit on a 24 GiB card — the transformer alone is 26.3 GiB — while both quantized builds run resident. It is 1.78x faster than the INT4 build here.

Dense reference (left) and this build (right). Same prompt, seed, scheduler, resolution, and step count. Pixel MAE 8.18 / RMSE 19.92, versus 16.01 / 34.05 for the INT4 build.
Requires the Hugging Face kernels package and DIFFUSERS_TRUST_REMOTE_KERNELS=true,
plus a Diffusers build with the nunchaku_lite quantizer. NVFP4 needs
a Blackwell or newer NVIDIA GPU; Hopper is unsupported. On Turing through Ada use the INT4 build instead.
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained(
"lite-infer/krea-2-turbo-nunchaku-lite-nvfp4-r32",
torch_dtype=torch.bfloat16,
).to("cuda")
image = pipe(
prompt="a fox in the snow",
generator=torch.Generator("cuda").manual_seed(12345),
width=1024,
height=1024,
num_inference_steps=8,
guidance_scale=0.0,
).images[0]
image.save("output.png")