flux weights needs about 7.0 GB of memory at Q5_K_S (a 3.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 3.3 GB (Q5_K_S) to 8.3 GB (Q5_K_S).
flux weights is a 11.9B-parameter Flux model in GGUF format, quantized by farpluto. Its trained context length is 512 tokens. The repository has 2 quant files, from 3.3 GB (Q5_K_S) to 8.3 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 3.3 GB | 4.0 GB | Fits | Get file → | |
| Q5_K_S | 8.3 GB | 9.0 GB | Too big | Get file → |
What GPU do you need for flux weights?
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 Q5_K_S (3.3 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (8.3 GB file, about 12.0 GB in use).
Which flux weights quant should you choose?
Q5_K_S (3.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about flux weights
How much VRAM does flux weights need?
About 7.0 GB at Q5_K_S with an 8K context window. That is the 3.3 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 weights on an 8 GB GPU?
Yes, with Q5_K_S: the 3.3 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of flux weights GGUF?
It depends on the quant: Q5_K_S is 3.3 GB, Q5_K_S is 8.3 GB.
What context length does flux weights 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 weights GGUF?
The files are on Hugging Face in the farpluto/flux-weights 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 weights 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.