FLUX.1 dev needs about 13.2 GB of memory at Q4_1 (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 10.1 GB (Q4_0) to 34.1 GB.
FLUX.1 dev – 17 billion‑parameter image generation model
FLUX.1 dev is a 17 billion‑parameter rectified flow transformer that generates images from text. It is open‑weight and designed for efficient inference with guidance distillation. The model is available in multiple GGUF quantizations.
Good at
- Text‑to‑image generation
- Efficient inference with guidance distillation
- Open‑weight research
Limits
- Not intended for factual information
- May amplify societal biases
- No vision support beyond image generation
Best for
- Creative image generation
- Research on open‑weight models
- Developing custom workflows
Who it’s for. Developers and artists who need a high‑quality, open‑weight text‑to‑image model. The model is suitable for local inference with llama‑cpp or ComfyUI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 10.1 GB | 11.8 GB | Too big | Get file → | |
| Q4_0 | 10.3 GB | 12.0 GB | Too big | Get file → | |
| Q4_1 | 11.3 GB | 13.2 GB | Too big | Get file → | |
| Q8_0 | 18.5 GB | 21.2 GB | Too big | Get file → | |
| Q8_0 | 18.6 GB | 21.4 GB | Too big | Get file → | |
| — | 34.1 GB | 38.7 GB | Too big | Get file → |
For 8 GB VRAM use Q4_0 (10.08 GB file, ~11.8 GB memory). For 12 GB VRAM use Q4_1 (11.31 GB file, ~13.2 GB memory). For 16 GB VRAM use Q8_0 (18.51 GB file, ~21.2 GB memory).
What GPU do you need for FLUX.1 dev?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_0 (10.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_1 (11.3 GB file, about 13.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 21.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 21.4 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (34.1 GB file, about 38.7 GB in use).
Which FLUX.1 dev quant should you choose?
Q4_1 (11.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 10.1 GB, with the quality trade-offs that come with fewer bits. 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.1 dev
How much VRAM does FLUX.1 dev need?
About 13.2 GB at Q4_1 with an 8K context window. That is the 11.3 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 FLUX.1 dev on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of FLUX.1 dev GGUF?
It depends on the quant: Q4_0 is 10.1 GB, Q4_0 is 10.3 GB, Q4_1 is 11.3 GB, Q8_0 is 18.5 GB, Q8_0 is 18.6 GB, file is 34.1 GB.
Where can I download FLUX.1 dev GGUF?
The files are on Hugging Face in the gpustack/FLUX.1-dev-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.1 dev 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.1 dev on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 11.8 GB memory at 8k context, which fits in 8 GB VRAM with some overhead.
Is FLUX.1 dev open source?
The weights are open and can be used for personal, scientific, and commercial purposes under the Non‑Commercial License.
Does FLUX.1 dev provide factual answers?
No, the model is not intended to provide factual information and may amplify biases.