FL

Flux1 dev

FluxGGUF by mirek190Updated 2024-08-24
Download on Hugging Face
Parameters4.76B
Context512
Layers—
Architectureflux
Smallest quant5.1 GB
Quick answer

Flux1 dev needs about 8.3 GB of memory at Q4_K_M (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 5.1 GB to 12.7 GB (Q8_0).

Flux1 dev is a 4.76B-parameter Flux model in GGUF format, quantized by mirek190. Its trained context length is 512 tokens. The repository has 4 quant files, from 5.1 GB to 12.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.1 GB 5.6 GB
Fits Get file →
Q4_06.8 GB 7.3 GB
Tight Get file →
Q4_K_M6.9 GB 7.5 GB
Tight Get file →
Q8_012.7 GB 13.3 GB
Too big Get file →

What GPU do you need for Flux1 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: the best quant that fits is the main file (5.1 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (6.9 GB file, about 8.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).

Which Flux1 dev quant should you choose?

Q4_K_M is the usual starting point for Flux1 dev: it balances file size and quality well. Here it is a 6.9 GB file.

The Q8_0 file is 12.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 5.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters4.76B
Trained context512 tokens

Source

Quantized bymirek190
FamilyFlux
Licenseother
Downloads (HF)118
Last updated2024-08-24

Frequently asked questions about Flux1 dev

How much VRAM does Flux1 dev need?

About 8.3 GB at Q4_K_M 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 Flux1 dev on an 8 GB GPU?

Yes, with the smaller files: the 5.1 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Flux1 dev GGUF?

It depends on the quant: file is 5.1 GB, Q4_0 is 6.8 GB, Q4_K_M is 6.9 GB, Q8_0 is 12.7 GB.

What context length does Flux1 dev support?

The GGUF header lists a trained context length of 512 tokens (512).

Where can I download Flux1 dev GGUF?

The files are on Hugging Face in the mirek190/Flux1_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 Flux1 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.

Similar models

Browse all →

More from mirek190

All by mirek190 →

More Flux models

All Flux →

Other small models

All small models →