Sakura FLUX.3 Image Klein PromptUpsampler 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 4 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 4.4 GB.
Sakura FLUX.3 Image Klein Prompt Upsampler Uncensored – a vision‑language prompt upsampler
Sakura FLUX.3 Image Klein Prompt Upsampler expands short image requests into detailed captions for FLUX.3 image models. It accepts up to 10 reference images and optional bounding boxes. The model is a fine‑tune of Qwen3.5‑9B with vision weights frozen.
Good at
- Expands short image prompts into detailed captions
- Supports reference images and bounding boxes
- Uncensored language weights for broader content
Limits
- No vision model included – requires separate FLUX.3 image model
- Requires Apache‑2.0 licensed components
- Large memory footprint for higher quantizations
Best for
- Text‑to‑image pipelines needing detailed prompts
- Image editing workflows with reference images
- Layout generation with bounding boxes
Who it’s for. Developers building text‑to‑image or image editing systems that use FLUX.3. It is suitable for users who need a dedicated prompt upsampler and are comfortable integrating separate vision and text encoder components.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.63 GB, estimated 7.2 GB memory). For 12 GB VRAM, Q5_K_M (6.47 GB, 8.1 GB memory) is suitable. For larger budgets, Q6_K or Q8_0 can be used, but they require 9–11 GB memory.
What GPU do you need for Sakura FLUX.3 Image Klein PromptUpsampler 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 FLUX.3 Image Klein PromptUpsampler Uncensored quant should you choose?
Q4_K_M is the usual starting point for Sakura FLUX.3 Image Klein PromptUpsampler 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 FLUX.3 Image Klein PromptUpsampler Uncensored
How much VRAM does Sakura FLUX.3 Image Klein PromptUpsampler 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 FLUX.3 Image Klein PromptUpsampler 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 FLUX.3 Image Klein PromptUpsampler Uncensored GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, Q8_0 is 9.5 GB.
What context length does Sakura FLUX.3 Image Klein PromptUpsampler 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 4.4 GB at 32K.
Where can I download Sakura FLUX.3 Image Klein PromptUpsampler Uncensored GGUF?
The files are on Hugging Face in the webmp3/Sakura-FLUX.3-Image-Klein-PromptUpsampler-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 FLUX.3 Image Klein PromptUpsampler Uncensored use?
Hugging Face lists the license as apache-2.0. 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 Sakura FLUX.3 on 8 GB VRAM?
Yes, with the Q4_K_M quantization it uses about 7.2 GB of VRAM, which fits within an 8 GB budget.
Does this model support vision tasks?
It is a prompt upsampler; it does not contain a vision encoder and must be paired with a separate FLUX.3 image model.
What license applies to this model?
The model is released under Apache‑2.0, and the repository includes a LICENSE file.