---
title: AWPortrait-FL-GGUF
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/AWPortrait-FL-GGUF"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/AWPortrait-FL-GGUF.md"
repository: AI-ModelScope/AWPortrait-FL-GGUF
last_updated: 2024-11-22
license: other
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 1788
stars: 0
tags:
  - gguf
---

# AWPortrait-FL-GGUF

> AWPortrait-FL-GGUF - AI-ModelScope 在 ModelScope 开源的模型。GGUF quants of https://huggingface.co/Shakker-Labs/AWPortrait-FL/ made using instructions from https://github.com/city96/ComfyUI-GGUF/ . This is my first time quantizing anything. I find the Q80 version…

AI-ModelScope/AWPortrait-FL-GGUF 是 ModelScope 魔搭社区上的机器学习模型，采用 other 许可。

- **Repository**: AI-ModelScope/AWPortrait-FL-GGUF
- **License**: other
- **Tags**: gguf
- **Downloads**: 1788
- **Stars**: 0
- **Last updated**: 2024-11-22

Source: https://www.modelscope.cn/models/AI-ModelScope/AWPortrait-FL-GGUF

---

GGUF quants of https://huggingface.co/Shakker-Labs/AWPortrait-FL/ made using instructions from https://github.com/city96/ComfyUI-GGUF/ .
This is my first time quantizing anything. I find the Q8_0 version of Flux Dev fp16 to be the best one to use, so I wanted to be able
to have Q8_0 quants of finetuned models as  they come out.

The K quants do not work with Forge as of 2024/09/06. I used a fork (https://github.com/mhnakif/ComfyUI-GGUF/) to make
Q4_0, Q5_0, Q8_0 and F16, which do work in Forge.