FLUX.2 klein 9B needs about 7.1 GB of memory at Q4_K_M (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 4.0 GB (Q2_K) to 18.2 GB (F16).
FLUX.2 klein 9B – 9 billion‑parameter flow transformer for real‑time image generation
FLUX.2 klein 9B is a 9 billion‑parameter rectified flow transformer that generates images from text and supports multi‑reference editing. It is distilled to four inference steps, enabling sub‑second generation with high quality. The model is available in GGUF format and is licensed for non‑commercial use.
Good at
- Sub‑second image generation
- Text‑to‑image and image‑to‑image editing
- High prompt adherence
Limits
- No vision support beyond image generation
- Requires 8 k context for estimates
- Non‑commercial license
Best for
- Real‑time creative apps
- Rapid prototyping of image generation
- Interactive editing tools
Who it’s for. Developers and creatives building real‑time image generation or editing applications. The model is suitable for projects that need fast inference and high visual quality without large compute resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_0 | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 5.8 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q4_1 | 6.2 GB | 7.4 GB | Tight | Get file → | |
| Q5_0 | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_S | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q5_K_M | 7.0 GB | 8.4 GB | Too big | Get file → | |
| Q5_1 | 7.3 GB | 8.6 GB | Too big | Get file → | |
| Q6_K | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q8_0 | 10.0 GB | 11.7 GB | Too big | Get file → | |
| BF16 | 18.2 GB | 20.8 GB | Too big | Get file → | |
| F16 | 18.2 GB | 20.8 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.91 GB) or Q4_K_S (5.83 GB) are suitable, with estimated memory around 7–7.1 GB at 8 k context. For 12 GB VRAM, Q5_K_M (7.02 GB) or Q5_K_S (6.94 GB) provide higher quality while staying within memory limits. Larger quants such as Q6_K or Q8_0 exceed typical VRAM budgets.
What GPU do you need for FLUX.2 klein 9B?
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 Q3_K_M (4.8 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_0 (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 11.7 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (18.2 GB file, about 20.8 GB in use).
Which FLUX.2 klein 9B quant should you choose?
Q4_K_M is the usual starting point for FLUX.2 klein 9B: it balances file size and quality well. Here it is a 5.9 GB file.
The Q8_0 file is 10.0 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 at 4.0 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.2 klein 9B
How much VRAM does FLUX.2 klein 9B need?
About 7.1 GB at Q4_K_M with an 8K context window. That is the 5.9 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.2 klein 9B on an 8 GB GPU?
Yes, with Q5_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.2 klein 9B GGUF?
It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 4.7 GB, Q3_K_M is 4.8 GB, Q4_0 is 5.6 GB, Q4_K_S is 5.8 GB, Q4_K_M is 5.9 GB and 9 more.
Where can I download FLUX.2 klein 9B GGUF?
The files are on Hugging Face in the drends/FLUX.2-klein-9B-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.2 klein 9B 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.2 klein 9B on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantizations, which are about 5.9 GB in size and require roughly 7–7.1 GB of VRAM at 8 k context.
Does the model support image editing?
Yes, it supports multi‑reference editing and image‑to‑image generation within the same model.
What license applies to this model?
The model is available for non‑commercial use under its current license.