Flux 3 Klein needs about 4.0 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 2.9 GB to 5.9 GB (Q8_0).
Flux 3 Klein – 5.6B parameter diffusion model for text‑to‑image and reference editing
Flux 3 Klein is a 5.6B parameter diffusion transformer from Black Forest Labs. It accepts a text prompt and up to 10 reference images to generate or edit images. The model supports bounding‑box coordinates for spatial layout control.
Good at
- Text‑to‑image generation
- Reference‑based image editing
- Spatial layout control via bounding boxes
Limits
- No vision support beyond image editing
- Requires up to 7.1 GB VRAM for Q8_0
- License is other, not open‑weights
Best for
- Creative image generation
- Editing existing artwork
- Designing scenes with spatial constraints
Who it’s for. Artists and designers who need a lightweight diffusion model for generating or editing images from text prompts and reference images. The model is suitable for users with moderate GPU memory and those working within ComfyUI workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.9 GB | 3.8 GB | Fits | Get file → | |
| — | 3.0 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q6_K | 4.5 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 4.6 GB | 5.6 GB | Fits | Get file → | |
| — | 5.5 GB | 6.7 GB | Fits | Get file → | |
| — | 5.6 GB | 6.7 GB | Fits | Get file → | |
| Q8_0 | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 5.9 GB | 7.1 GB | Fits | Get file → |
For GPUs with about 4 GB VRAM, use the Q4_K_M quantization (file size 3.12 GB, memory 4 GB). For 5–6 GB VRAM, Q6_K (file size 4.54 GB, memory 5.6 GB) is appropriate. For 7 GB or more, Q8_0 (file size 5.88 GB, memory 7.1 GB) provides the highest precision.
What GPU do you need for Flux 3 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: the best quant that fits is Q4_K_M (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.6 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.9 GB file, about 7.1 GB in use).
Which Flux 3 Klein quant should you choose?
Q4_K_M is the usual starting point for Flux 3 Klein: it balances file size and quality well. Here it is a 3.1 GB file.
The Q8_0 file is 5.9 GB, about 1.9 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.
If memory is tight, the smallest file is the first one in the table at 2.9 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 Klein
How much VRAM does Flux 3 Klein need?
About 4.0 GB at Q4_K_M with an 8K context window. That is the 3.1 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 Klein on an 8 GB GPU?
Yes, with Q8_0: the 5.9 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 Klein GGUF?
It depends on the quant: file is 2.9 GB, file is 3.0 GB, Q4_K_M is 3.1 GB, Q4_K_M is 3.1 GB, Q6_K is 4.5 GB, Q6_K is 4.6 GB and 4 more.
Where can I download Flux 3 Klein GGUF?
The files are on Hugging Face in the molbal/Flux-3-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 Flux 3 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 Flux 3 Klein on a GPU with 8 GB VRAM?
Yes, the Q8_0 quantization requires about 7.1 GB VRAM, so an 8 GB GPU can run it with some headroom.
Does Flux 3 Klein support reference image editing?
Yes, the model accepts up to 10 reference images to generate or edit images.
What is the context length for this model?
The model does not specify a trained context token length; context length is not provided.