---
title: FLUX.2-dev-gguf
canonical_url: "https://www.modelscope.cn/models/city96/FLUX.2-dev-gguf"
md_url: "https://www.modelscope.cn/models/city96/FLUX.2-dev-gguf.md"
repository: city96/FLUX.2-dev-gguf
last_updated: 2025-11-30
license: other
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.2-dev
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 4629
stars: 9
tags:
  - image-generation
  - image-editing
  - flux
  - diffusion-single-file
  - gguf
---

# FLUX.2-dev-gguf

> FLUX.2-dev-gguf - city96 在 ModelScope 开源的模型。This is a direct GGUF conversion of black-forest-labs/FLUX.2-dev.

city96/FLUX.2-dev-gguf 是 ModelScope 魔搭社区上的image-to-image模型，采用 other 许可，基于 black-forest-labs/FLUX.2-dev 构建。

- **Repository**: city96/FLUX.2-dev-gguf
- **License**: other
- **Tasks**: image-to-image
- **Base model**: black-forest-labs/FLUX.2-dev
- **Tags**: image-generation, image-editing, flux, diffusion-single-file, gguf
- **Downloads**: 4629
- **Stars**: 9
- **Last updated**: 2025-11-30

Source: https://www.modelscope.cn/models/city96/FLUX.2-dev-gguf

---

This is a direct GGUF conversion of [black-forest-labs/FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev).

The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node. Place the required model(s) in the following folders:

| Type         | Name                                | Location                          | Download         |
| ------------ | ----------------------------------- | --------------------------------- | ---------------- |
| Main Model   | flux2-dev                           | `ComfyUI/models/diffusion_models` | GGUF (this repo) |
| Text Encoder | Mistral-Small-3.2-24B-Instruct-2506 | `ComfyUI/models/text_encoders`    | [Safetensors](https://huggingface.co/Comfy-Org/flux2-dev/tree/main/split_files/text_encoders) / [GGUF](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/tree/main) |
| VAE          | flux2 VAE                           | `ComfyUI/models/vae`              | [Safetensors](https://huggingface.co/Comfy-Org/flux2-dev/blob/main/split_files/vae/flux2-vae.safetensors) |

[**Example outputs**](media/flux2dev-image.jpg) - sample size of 1, not strictly representative

![sample](media/flux2dev-image.jpg)

### Notes

> [!NOTE]
> As with Qwen-Image, Q5_K_M, Q4_K_M, Q3_K_M, Q3_K_S and Q2_K have some extra logic as to which blocks to keep in high precision.
> 
> The logic is partially based on guesswork, trial & error, and the graph found in the readme for [Freepik/flux.1-lite-8B](https://huggingface.co/Freepik/flux.1-lite-8B#motivation) (which in turn quotes [this blog by Ostris](https://ostris.com/2024/09/07/skipping-flux-1-dev-blocks/))

*As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*