flux 3 image klein needs about 4.6 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.6 GB (Q2_K_XL) to 11.1 GB (BF16).
Flux 3 Image Klein – 5.6B image transformer for text‑to‑image and editing
Flux 3 Image Klein is a 5.55B parameter image transformer. It supports text‑to‑image generation and image editing with up to ten reference images. The model uses Qwen3‑VL‑4B‑Instruct as the text encoder and a VAE unchanged from the original checkpoint.
Good at
- Text‑to‑image generation
- Image editing with reference images
- Efficient inference with GGUF quantization
Limits
- No vision support beyond image generation
- Requires separate text encoder and VAE
- License type is other, not open source
Best for
- Generating images from prompts
- Editing images with reference guidance
- Running on GPUs with limited VRAM using low‑bit quantizations
Who it’s for. Developers and researchers needing a lightweight image transformer for generation and editing tasks. The model is suitable for users who can supply the Qwen3‑VL‑4B‑Instruct encoder and VAE from the original repository.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_XL | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_M | 3.0 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_XL | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_XL | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_M | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q5_K_XL | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q6_K | 4.8 GB | 5.9 GB | Fits | Get file → | |
| Q8_0 | 6.1 GB | 7.3 GB | Tight | Get file → | |
| BF16 | 11.1 GB | 12.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K_XL (2.62 GB, 3.4 GB memory). For 12 GB VRAM, Q4_K_XL (3.93 GB, 4.9 GB memory). For higher fidelity, Q8_0 (6.09 GB, 7.3 GB memory) gives output closest to bf16. Memory estimates are approximate.
What GPU do you need for 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: the best quant that fits is Q3_K_M (3.0 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.8 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.1 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (6.1 GB file, about 7.3 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (11.1 GB file, about 12.9 GB in use).
Which flux 3 image klein quant should you choose?
Q4_K_M is the usual starting point for flux 3 image klein: it balances file size and quality well. Here it is a 3.7 GB file.
The Q8_0 file is 6.1 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.
If memory is tight, the smallest file is Q2_K_XL at 2.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flux 3 image klein
How much VRAM does flux 3 image klein need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.7 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 on an 8 GB GPU?
Yes, with Q8_0: the 6.1 GB file needs about 7.3 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 GGUF?
It depends on the quant: Q2_K_XL is 2.6 GB, Q3_K_M is 3.0 GB, Q3_K_XL is 3.3 GB, Q4_K_M is 3.7 GB, Q4_K_XL is 3.9 GB, Q5_K_M is 4.2 GB and 4 more.
Where can I download flux 3 image klein GGUF?
The files are on Hugging Face in the unsloth/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 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 Flux 3 Image Klein on 8 GB VRAM?
Yes, use the Q2_K_XL quantization which is 2.62 GB and requires about 3.4 GB VRAM at 8k context.
Does the model support image editing?
Yes, it can edit images using up to ten reference images with the same model used for generation.
Do I need the original text encoder?
Yes, the Qwen3‑VL‑4B‑Instruct encoder and VAE are unchanged and must be supplied separately.