FL

Sakura FLUX.3 Image Klein

FluxGGUF by webmp3Updated 2026-10-16
Download on Hugging Face
Parameters5.55B
Context—
Layers—
Architectureflux
Smallest quant3.3 GB
Quick answer

Sakura FLUX.3 Image Klein needs about 4.2 GB of memory at Q4_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 3.3 GB (Q4_K_M) to 6.0 GB (Q8_0).

Sakura FLUX.3 Image Klein – 5.55B parameter image model in GGUF format

Sakura FLUX.3 Image Klein is a 5.55B parameter image model built with FLUX. It is community‑quantized and uses the official Qwen3‑VL‑4B‑Instruct text encoder. The model is distributed under the FLUX Kommunity License for non‑commercial use or qualified commercial use.

Good at

  • Image generation with 16 steps
  • Fast inference with low‑precision quants
  • Compatible with ComfyUI and llama.cpp

Limits

  • No vision support in the text encoder
  • License restricts commercial use of outputs
  • Requires 8k context for full performance

Best for

  • Creating art with limited VRAM
  • Running on mid‑range GPUs
  • Generating images for non‑commercial projects

Who it’s for. Developers and artists who need a lightweight FLUX image model for local inference. It is suitable for hobbyists and researchers working on image generation without commercial constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.3 GB 4.2 GB
Fits Get file →
Q5_K_M4.0 GB 4.9 GB
Fits Get file →
—4.3 GB 5.3 GB
Fits Get file →
Q6_K4.7 GB 5.7 GB
Fits Get file →
Q8_06.0 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 3.27 GB, memory 4.2 GB at 8k context). If 12 GB VRAM is available, Q5_K_M (3.95 GB, 4.9 GB) or Q6_K (4.67 GB, 5.7 GB) provide better quality. Q8_0 offers the highest fidelity but needs 7.2 GB memory at 8k context.

What GPU do you need for Sakura FLUX.3 Image Klein?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q6_K (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.0 GB file, about 7.2 GB in use).

Which Sakura FLUX.3 Image Klein quant should you choose?

Q4_K_M is the usual starting point for Sakura FLUX.3 Image Klein: it balances file size and quality well. Here it is a 3.3 GB file.

The Q8_0 file is 6.0 GB, about 1.8 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

Architectureflux
Parameters5.55B

Source

Quantized bywebmp3
FamilyFlux
Licenseother
Downloads (HF)5,778
Last updated2026-10-16

Frequently asked questions about Sakura FLUX.3 Image Klein

How much VRAM does Sakura FLUX.3 Image Klein need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 3.3 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 on an 8 GB GPU?

Yes, with Q8_0: the 6.0 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 GGUF?

It depends on the quant: Q4_K_M is 3.3 GB, Q5_K_M is 4.0 GB, file is 4.3 GB, Q6_K is 4.7 GB, Q8_0 is 6.0 GB.

Where can I download Sakura FLUX.3 Image Klein GGUF?

The files are on Hugging Face in the webmp3/Sakura-FLUX.3-Image-Klein-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 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 Sakura FLUX.3 Image Klein on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.2 GB memory at 8k context, fitting within 8 GB VRAM.

Is the model suitable for commercial use?

The FLUX Kommunity License allows commercial use of outputs only under specific conditions; review the license for details.

Does the model support text‑to‑image only?

Yes, the image model works with the Qwen3‑VL‑4B‑Instruct text encoder for text‑to‑image generation.

Other GGUFs of flux-3-image-klein

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Flux models

All Flux →

Other small models

All small models →