FLUX.2 klein base 4B needs about 3.3 GB of memory at Q4_0 (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.5 GB (Q4_0) to 4.3 GB (Q8_0).
FLUX.2 klein base 4B – compact 4B parameter image model for real‑time generation
FLUX.2 klein base 4B is a 4 billion parameter rectified flow transformer. It generates images from text and supports multi‑reference editing. The model is open‑licensed under Apache 2.0 and runs on consumer hardware with as little as 13 GB VRAM.
Good at
- Real‑time image generation under a second
- High quality with small model size
- Fine‑tuning and LoRA training friendly
Limits
- No factual knowledge or text accuracy
- May produce distorted text output
- Requires at least 13 GB VRAM for full performance
Best for
- Local image generation pipelines
- Fine‑tuning for custom art styles
- Research on flow‑based image models
Who it’s for. Developers and artists who need a fast, small image model that can be run locally and fine‑tuned. The model is suitable for research and creative projects where control and speed are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 5.3 GB | Fits | Get file → |
For 8 GB VRAM use the Q4_0 quant (2.46 GB file, ~3.3 GB memory at 8k context). For 12 GB VRAM use Q8_0 (4.3 GB file, ~5.3 GB memory). Estimates are approximate.
What GPU do you need for FLUX.2 klein base 4B?
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_0 (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
Which FLUX.2 klein base 4B quant should you choose?
Q4_0 (2.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FLUX.2 klein base 4B
How much VRAM does FLUX.2 klein base 4B need?
About 3.3 GB at Q4_0 with an 8K context window. That is the 2.5 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.2 klein base 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.2 klein base 4B GGUF?
It depends on the quant: Q4_0 is 2.5 GB, Q8_0 is 4.3 GB.
Where can I download FLUX.2 klein base 4B GGUF?
The files are on Hugging Face in the leejet/FLUX.2-klein-base-4B-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 base 4B 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 FLUX.2 klein base 4B on 8 GB VRAM?
The Q4_0 quant uses about 3.3 GB of VRAM at 8k context, so it can run on 8 GB VRAM with headroom for other processes.
Is the model suitable for text generation?
No, the model is not intended for factual text generation and may produce inaccurate or distorted text.
Can I use the model for commercial image production?
Yes, outputs can be used commercially under the Apache 2.0 license.