FL

FLUX-3-Image-Klein-pup

FluxGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant4.7 GB
Quick answer

FLUX-3-Image-Klein-pup needs about 7.1 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 4 quants, from 4.7 GB (IQ3_S) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

FLUX‑3‑Image‑Klein‑pup: 9B vision‑language prompt upsampler

FLUX‑3‑Image‑Klein‑pup is a 9B fine‑tune of Qwen3.5‑9B that expands short image requests into detailed captions. It accepts up to 10 reference images and optional bounding boxes. The model is optimized for use with FLUX 3 Image Klein as a prompt upsampler.

Good at

  • Expanding short image prompts into ~200‑word captions
  • Handling reference images and bounding boxes
  • Fine‑tuned for FLUX 3 Image Klein workflow

Limits

  • Not a standalone text‑to‑image model
  • Requires a prompt upsampler to function
  • License: apache‑2.0

Best for

  • Text‑to‑image pipelines needing detailed prompts
  • Image editing with reference guidance
  • Layout generation with bounding boxes

Who it’s for. Developers building FLUX 3 Image Klein pipelines who need a lightweight prompt upsampler. The model is ideal for systems that already use FLUX 3 Image Klein and require richer captions from concise prompts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S4.7 GB 6.3 GB
Fits Get file →
IQ4_XS5.5 GB 7.1 GB
Fits Get file →
Q5_K_M6.6 GB 8.1 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →

For 8 GB VRAM, use IQ3_S (file size 4.68 GB, estimated memory 6.3 GB at 8 k context). For 12 GB VRAM, IQ4_XS (5.51 GB, 7.1 GB) or Q5_K_M (6.57 GB, 8.1 GB) are suitable. The Q8_0 quant (9.53 GB, 11.1 GB) requires more than 12 GB VRAM.

What GPU do you need for FLUX-3-Image-Klein-pup?

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 IQ4_XS (5.5 GB file, about 7.1 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 FLUX-3-Image-Klein-pup 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 IQ3_S at 4.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byAtomicChat
FamilyFlux
Licenseapache-2.0
Downloads (HF)2,255
Last updated2026-10-28

Frequently asked questions about FLUX-3-Image-Klein-pup

How much VRAM does FLUX-3-Image-Klein-pup need?

About 7.1 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 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.5 GB file needs about 7.1 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 GGUF?

It depends on the quant: 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.

What context length does FLUX-3-Image-Klein-pup 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 FLUX-3-Image-Klein-pup GGUF?

The files are on Hugging Face in the AtomicChat/FLUX-3-Image-Klein-pup-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 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 IQ3_S quant uses 6.3 GB of VRAM at 8 k context, fitting within an 8 GB budget.

Does the model support text generation?

No, it is designed only as a prompt upsampler for FLUX 3 Image Klein and does not generate images directly.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of flux-3-image-klein-pup

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More Flux models

All Flux →

Other small models

All small models →