Flux needs about 10.5 GB of memory at Q4_K_S (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 2.7 GB (Q4_K_S) to 6.8 GB (Q4_K_S).
Flux: 4.76B parameter text-to-image model in GGUF format
Flux is a 4.76B parameter text‑to‑image model based on a t5encoder architecture. It is available in GGUF format with Q4_K_S quantization. The model is licensed under apache‑2.0 and supports 512‑token context.
Good at
- Text‑to‑image generation
- Supports 512‑token prompts
- Compatible with ComfyUI workflows
Limits
- No vision input support
- Requires 8‑k context for memory estimates
- Only Q4_K_S quant available
Best for
- Generating images from text prompts
- Fine‑tuning with LoRA
- Integrating into ComfyUI pipelines
Who it’s for. Developers and artists who need a lightweight, open‑source text‑to‑image model for local inference. The model is suitable for users with moderate GPU memory and those who prefer GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 2.7 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 6.8 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_S | 6.8 GB | 7.5 GB | Tight | Get file → |
For 8‑GB VRAM, use the 2.74‑GB Q4_K_S file; it estimates 6.5‑GB memory at 8‑k context. For 12‑GB VRAM, the 6.78‑GB or 6.81‑GB Q4_K_S files are suitable, estimating 10.5‑GB memory. Memory estimates are approximate.
What GPU do you need for Flux?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is Q4_K_S (2.7 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (6.8 GB file, about 10.5 GB in use).
Which Flux quant should you choose?
Q4_K_S (6.8 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_K_S at 2.7 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
How much VRAM does Flux need?
About 10.5 GB at Q4_K_S with an 8K context window. That is the 6.8 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 on an 8 GB GPU?
Yes, with Q4_K_S: the 2.7 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 GGUF?
It depends on the quant: Q4_K_S is 2.7 GB, Q4_K_S is 6.8 GB, Q4_K_S is 6.8 GB.
What context length does Flux support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.
Where can I download Flux GGUF?
The files are on Hugging Face in the StableDiffusionVN/Flux 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 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 on 8 GB VRAM?
Yes, the 2.74‑GB Q4_K_S file can run on 8‑GB VRAM, with an estimated 6.5‑GB memory usage at 8‑k context.
Does Flux support image‑to‑image tasks?
Flux supports image‑to‑image workflows via ComfyUI nodes such as Img‑Img and Inpaint.