---
title: Fluxmania-SVDQ
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Fluxmania-SVDQ"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Fluxmania-SVDQ.md"
repository: AI-ModelScope/Fluxmania-SVDQ
last_updated: 2025-10-22
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 21.3B
tensor_type:
  - BF16
  - I8
  - I32
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 112
stars: 0
tags:
  - Flux1
  - SVDQaunt
  - SVDQ
  - Quantization
  - Fluxmania
  - Legacy
---

# Fluxmania-SVDQ

> Fluxmania-SVDQ - AI-ModelScope 在 ModelScope 开源的模型。This repository contains Nunchaku-quantized (SVDQ) versions of Fluxmania Legacy, a text-to-image model based on Flux.1 Dev by AdelAI

- **Repository**: AI-ModelScope/Fluxmania-SVDQ
- **Tasks**: text-to-image-synthesis
- **Parameters**: 21.3B
- **Tags**: Flux1, SVDQaunt, SVDQ, Quantization, Fluxmania, Legacy
- **Downloads**: 112
- **Stars**: 0
- **Last updated**: 2025-10-22

Source: https://www.modelscope.cn/models/AI-ModelScope/Fluxmania-SVDQ

---

This repository contains Nunchaku-quantized (SVDQ) versions of [Fluxmania Legacy](https://civitai.com/models/778691?modelVersionId=1769925), a text-to-image model based on Flux.1 Dev by [Adel_AI](https://civitai.com/user/Adel_AI)

If you like the model, please consider liking, reviewing and tipping the creator. 

Model Files
- [svdq-int4_r32-fluxmania-legacy.safetensors](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/svdq-int4_r32-fluxmania-legacy.safetensors): SVDQuant INT4 (rank 32) Fluxmania Legacy model. For users with non-Blackwell GPUs (pre-50-series).
- [svdq-fp4_r32-fluxmania-legacy.safetensors](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/svdq-fp4_r32-fluxmania-legacy.safetensors): SVDQuant NVFP4 (rank 32) Fluxmania Legacy model. For users with Blackwell GPUs (50-series).

[Comfyui Workflow
](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/fluxmania_workflow.json)
### Quality Evaluation

Below is the quality and similarity evaluated with 256 samples from MJHQ-30K dataset. (BF16 is the unqauntized model. INT W4A4 is INT4 and NVFP4 is FP4)

| Model                      | Precision |  Method   | FID                | IR              | LPIPS                | PSNR              |
|----------------------------|-----------|-----------|--------------------|-----------------|----------------------|-------------------|
| Fluxmania Legacy (25 step) | BF16      | --        | 175.08             | 0.895           | --                   | --                |
|                            | INT W4A4  | SVDQ      | 174.84             | 0.795           | 0.222                | 22.84             |
|                            | NVFP4     | SVDQ      | 173.10             | 0.884           | 0.192                | 23.38             |

If you find these useful please consider: <a href='https://ko-fi.com/B0B21MPRDT' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>