Qwen-Image-2.1-PE-I2I needs about 11.1 GB of memory at Q8_0 (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwen-Image-2.1-PE-I2I: Prompt rewriting for image editing
Qwen-Image-2.1-PE-I2I is a fine‑tuned Qwen3.5‑VL 9B model that rewrites vague editing instructions into precise prompts for downstream image editing. It supports up to 10 reference images and outputs JSON with expanded prompt and aspect ratio information.
Good at
- Precise prompt generation for image editing
- Multi‑image reference handling
- JSON output for downstream pipelines
Limits
- Requires 11.1 GB VRAM at 8 k context
- No vision support beyond prompt rewriting
- License is Qwen Research License Agreement
Best for
- Local prompt enhancement before image generation
- Automated editing workflows
- Integrating with diffusers for image editing
Who it’s for. Developers building local image editing pipelines who need a lightweight prompt rewriting step. The model is suitable for users who prefer local inference with llama.cpp and do not require large‑scale vision tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
The only available quant is Q8_0, 9.53 GB file size. It requires approximately 11.1 GB VRAM at 8 k context. For 12 GB VRAM systems, Q8_0 is recommended. No other quants are listed.
What GPU do you need for Qwen-Image-2.1-PE-I2I?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which Qwen-Image-2.1-PE-I2I quant should you choose?
Q8_0 (9.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen-Image-2.1-PE-I2I
How much VRAM does Qwen-Image-2.1-PE-I2I need?
About 11.1 GB at Q8_0 with an 8K context window. That is the 9.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen-Image-2.1-PE-I2I on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen-Image-2.1-PE-I2I GGUF?
It depends on the quant: Q8_0 is 9.5 GB.
What context length does Qwen-Image-2.1-PE-I2I support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Qwen-Image-2.1-PE-I2I GGUF?
The files are on Hugging Face in the lightx2v/Qwen-Image-2.1-PE-I2I-GGUF-Q8_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen-Image-2.1-PE-I2I use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
No. The Q8_0 quant needs about 11.1 GB VRAM at 8 k context, so 8 GB is insufficient.
Does it support vision tasks?
It rewrites prompts for image editing but does not process images directly; it expects image inputs via arguments.
What is the maximum context length?
The model was trained with 262144 context tokens.