FLUX.1 dev needs about 8.3 GB of memory at Q4_0 (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 4.2 GB (Q2_K) to 12.8 GB (Q8_0).
FLUX.1 dev – 11.9B parameter text‑to‑image model in GGUF format
FLUX.1 dev is a 11.9B parameter text‑to‑image model converted to GGUF. It is available in several quantizations ranging from Q2_K to Q8_0. The quantized files support stable‑diffusion.cpp for inference on GPUs with 4–6 GB VRAM.
Good at
- Text‑to‑image generation
- Low‑VRAM inference
- Fast generation with stable‑diffusion.cpp
Limits
- No vision support
- License follows original model
- No context length info
Best for
- Generating images from prompts on modest GPUs
- Rapid prototyping of image generation pipelines
- Educational demos of text‑to‑image models
Who it’s for. Developers and researchers needing a lightweight text‑to‑image model for local inference. The model is suitable for those who prefer open‑source tools and can work within the provided license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q3_K | 5.4 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q4_K | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 12.8 GB | 14.9 GB | Too big | Get file → |
For 4 GB VRAM, use Q2_K (4.15 GB file, ~5.2 GB memory at 8k context). For 6 GB VRAM, Q3_K (5.35 GB file, ~6.5 GB memory) or Q4_0/Q4_K (6.93 GB file, ~8.3 GB memory). Q8_0 requires ~14.9 GB memory and is not recommended for low‑VRAM GPUs.
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: the best quant that fits is Q2_K (4.2 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K (5.4 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (6.9 GB file, about 8.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).
Which FLUX.1 dev quant should you choose?
Q4_0 (6.9 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 Q2_K at 4.2 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.1 dev
How much VRAM does FLUX.1 dev need?
About 8.3 GB at Q4_0 with an 8K context window. That is the 6.9 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.1 dev on an 8 GB GPU?
Yes, with Q3_K: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FLUX.1 dev GGUF?
It depends on the quant: Q2_K is 4.2 GB, Q3_K is 5.4 GB, Q4_0 is 6.9 GB, Q4_K is 6.9 GB, Q8_0 is 12.8 GB.
Where can I download FLUX.1 dev GGUF?
The files are on Hugging Face in the leejet/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.
Can I run FLUX.1 dev on a GPU with 4 GB VRAM?
Yes, the Q2_K quantization is designed for GPUs with 4 GB or 6 GB VRAM and uses about 5.2 GB of memory at 8k context.
What license applies to the quantized files?
The quantized files follow the license of the original FLUX.1‑dev model, as stated in the original LICENSE.md.
Does FLUX.1 dev support vision inputs?
No, the model does not support vision inputs; it is a text‑to‑image model only.