Sakura Qwen Image 2.1 PE I2I Uncensored needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_K_M) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Sakura Qwen Image 2.1 PE I2I Uncensored – prompt‑rewriting for image editing
Sakura Qwen Image 2.1 PE I2I Uncensored is a fine‑tuned Qwen3.5‑VL 9B model that rewrites vague editing instructions into precise prompts for image‑editing models. It supports multiple input images and outputs a JSON with the rewritten prompt and aspect‑ratio information.
Good at
- Precise prompt rewriting for image editing
- Handles up to 10 reference images
- Outputs JSON with aspect‑ratio data
Limits
- No safety filter – can produce harmful content
- Non‑commercial use only under Qwen Research License
- Requires Qwen3.5‑VL architecture
Best for
- Generating prompts for text‑to‑image models
- Automating multi‑image editing workflows
- Creating new compositions with specified aspect ratios
Who it’s for. Developers and researchers building image‑editing pipelines who need a dedicated prompt‑rewriting step. The model is suitable for internal tools where content moderation is handled separately.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quantized file (5.63 GB, ~7.2 GB memory at 8 k context). For 12 GB VRAM use the Q8_0 file (9.53 GB, ~11.1 GB memory at 8 k context). Estimates are approximate.
What GPU do you need for Sakura Qwen Image 2.1 PE I2I Uncensored?
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: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which Sakura Qwen Image 2.1 PE I2I Uncensored quant should you choose?
Q4_K_M is the usual starting point for Sakura Qwen Image 2.1 PE I2I Uncensored: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sakura Qwen Image 2.1 PE I2I Uncensored
How much VRAM does Sakura Qwen Image 2.1 PE I2I Uncensored need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Sakura Qwen Image 2.1 PE I2I Uncensored on an 8 GB GPU?
Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura Qwen Image 2.1 PE I2I Uncensored GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q8_0 is 9.5 GB.
What context length does Sakura Qwen Image 2.1 PE I2I Uncensored 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 Sakura Qwen Image 2.1 PE I2I Uncensored GGUF?
The files are on Hugging Face in the webmp3/Sakura-Qwen-Image-2.1-PE-I2I-Uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura Qwen Image 2.1 PE I2I Uncensored 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?
Yes, using the Q4_K_M quantized file which requires about 7.2 GB of VRAM at 8 k context.
Does this model have a safety filter?
No. The model is uncensored and can generate harmful content verbatim.
What license applies to this model?
It is licensed under the Qwen Research License Agreement and is for non‑commercial use only.