FLUX 3 Image Klein pup Uncensored needs about 6.7 GB of memory at IQ4_XS (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 0.0 GB to 17.9 GB (BF16).
FLUX 3 Image Klein Prompt Upsampler – 8.95B Qwen3.5 fine‑tune
FLUX 3 Image Klein Prompt Upsampler expands short image requests into detailed prompts for FLUX 3 Image Klein. It accepts up to 10 reference images and optional bounding boxes, returning a single prompt. The model is a fine‑tune of Qwen3.5‑9B and runs under the Apache 2.0 license.
Good at
- Prompt upsampling for text‑to‑image
- Reference‑image guided prompt generation
- Bounding‑box aware prompt creation
Limits
- No vision inference – only prompt generation
- Requires a prompt upsampler for image generation
- No built‑in refusal handling in the prompt upsampler
Best for
- Preparing prompts for FLUX 3 Image Klein text‑to‑image
- Editing workflows that need reference images
- Layout design with bounding boxes
Who it’s for. Developers and artists who use FLUX 3 Image Klein for image generation and need a dedicated prompt upsampler. The model is suitable for local deployment via llama.cpp or compatible frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_S | 4.7 GB | 5.7 GB | Fits | Get file → | |
| IQ4_XS | 5.5 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_M | 6.6 GB | 7.9 GB | Tight | Get file → | |
| Q8_0 | 9.5 GB | 11.2 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 20.6 GB | Too big | Get file → |
For 8 GB VRAM use the IQ4_XS file (5.51 GB, 6.7 GB memory at 8k context). For 12 GB VRAM the IQ4_XS or Q5_K_M (6.57 GB, 7.9 GB memory) are suitable. If memory allows, Q8_0 (9.53 GB, 11.2 GB memory) provides the highest precision.
What GPU do you need for FLUX 3 Image Klein pup Uncensored?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_S (4.7 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.6 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 20.6 GB in use).
Which FLUX 3 Image Klein pup Uncensored quant should you choose?
IQ4_XS (5.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FLUX 3 Image Klein pup Uncensored
How much VRAM does FLUX 3 Image Klein pup Uncensored need?
About 6.7 GB at IQ4_XS with an 8K context window. That is the 5.5 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 FLUX 3 Image Klein pup Uncensored on an 8 GB GPU?
Yes, with Q5_K_M: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX 3 Image Klein pup Uncensored GGUF?
It depends on the quant: file is 0.0 GB, IQ3_S is 4.7 GB, IQ4_XS is 5.5 GB, Q5_K_M is 6.6 GB, Q8_0 is 9.5 GB, BF16 is 17.9 GB.
What context length does FLUX 3 Image Klein pup Uncensored support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download FLUX 3 Image Klein pup Uncensored GGUF?
The files are on Hugging Face in the AtomicChat/FLUX-3-Image-Klein-pup-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 FLUX 3 Image Klein pup 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 this model on 8 GB VRAM?
Yes, the IQ4_XS quantized file is 5.51 GB and requires about 6.7 GB of VRAM at 8k context.
Does this model support vision inference?
No, it only generates prompts; a separate image model is required for vision tasks.
What license does it use?
The model is released under the Apache 2.0 license.