---
title: Qwen-Image-2.1-PE-I2I-GGUF
canonical_url: "https://www.modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF"
md_url: "https://www.modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF.md"
repository: prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF
last_updated: 2026-09-20
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
base_model:
  - Qwen/Qwen-Image-2.1-PE-I2I
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2527
stars: 7
tags:
  - text-generation-inference
  - llama-cpp
  - qwen
  - prompt-rewriting
  - image-editing
  - gguf
---

# Qwen-Image-2.1-PE-I2I-GGUF

> Qwen-Image-2.1-PE-I2I-GGUF - prithivMLmods 在 ModelScope 开源的模型。Qwen-Image-2.1-PE-I2I-GGUF

prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 other 许可，基于 Qwen/Qwen-Image-2.1-PE-I2I 构建。

- **Repository**: prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF
- **License**: other
- **Tasks**: image-text-to-text
- **Base model**: Qwen/Qwen-Image-2.1-PE-I2I
- **Tags**: text-generation-inference, llama-cpp, qwen, prompt-rewriting, image-editing, gguf
- **Downloads**: 2527
- **Stars**: 7
- **Last updated**: 2026-09-20

Source: https://www.modelscope.cn/models/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF

---

# **Qwen-Image-2.1-PE-I2I-GGUF**

> **Qwen-Image-2.1-PE-I2I** is an image-editing prompt rewriting model for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL-9B that takes a vague editing instruction plus one or more input images and expands it into a precise, actionable prompt suitable for downstream image editing. It supports multi-image inputs (referenced as `<image1>`, `<image2>`, etc.) for tasks like compositing a subject from one image into another's scene, reasons through a `<think>` block before outputting a structured JSON result containing the rewritten prompt plus either a `wh_ratio` (new aspect ratio for compositions) or `ratio_follow` (inherited aspect ratio for in-place edits) — the two fields being mutually exclusive. The rewritten prompt is designed to feed directly into the Qwen-Image-2.1 diffusion pipeline via Diffusers for the actual image edit, and the model is loaded through standard Transformers (`AutoModelForImageTextToText`) with a system prompt shipped alongside the checkpoint; it's released under the Qwen Research License Agreement.

> [!NOTE]
System Prompt — https://huggingface.co/Qwen/Qwen-Image-2.1-PE-I2I/blob/main/system_prompt.txt

## Model Files

   File Name | Quant Type | File Size | File Link |
 |-----------|------------|-----------|-----------|
 | Qwen-Image-2.1-PE-I2I.BF16.gguf | BF16 | 17.9 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.BF16.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q3_K_L.gguf | Q3_K_L | 4.93 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q3_K_L.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q3_K_M.gguf | Q3_K_M | 4.62 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q3_K_M.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q4_K_M.gguf | Q4_K_M | 5.63 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q4_K_M.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q4_K_S.gguf | Q4_K_S | 5.35 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q4_K_S.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q5_K_M.gguf | Q5_K_M | 6.47 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q5_K_M.gguf) |
 | Qwen-Image-2.1-PE-I2I.Q5_K_S.gguf | Q5_K_S | 6.31 GB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.Q5_K_S.gguf) |
 | Qwen-Image-2.1-PE-I2I.mmproj-bf16.gguf | mmproj-bf16 | 922 MB | [Download](https://huggingface.co/prithivMLmods/Qwen-Image-2.1-PE-I2I-GGUF/blob/main/Qwen-Image-2.1-PE-I2I.mmproj-bf16.gguf) |

## llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp