FL

FLUX.1 schnell

FluxGGUF by gpustackUpdated 2024-11-25
Download on Hugging Face
Parameters17B
Context—
Layers—
Architecture—
Smallest quant10.0 GB
Quick answer

FLUX.1 schnell needs about 13.1 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 10.0 GB (Q4_0) to 34.3 GB.

FLUX.1 schnell is a 17B-parameter Flux model in GGUF format, quantized by gpustack. The repository has 6 quant files, from 10.0 GB (Q4_0) to 34.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_010.0 GB 11.7 GB
Too big Get file →
Q4_010.2 GB 11.9 GB
Too big Get file →
Q4_111.3 GB 13.1 GB
Too big Get file →
Q8_018.5 GB 21.2 GB
Too big Get file →
Q8_018.6 GB 21.3 GB
Too big Get file →
—34.3 GB 38.9 GB
Too big Get file →

What GPU do you need for FLUX.1 schnell?

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 (10.2 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (11.3 GB file, about 13.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 21.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (34.3 GB file, about 38.9 GB in use).

Which FLUX.1 schnell 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 10.0 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

Parameters17B

Source

Quantized bygpustack
FamilyFlux
Licenseapache-2.0
Downloads (HF)357
Last updated2024-11-25

Frequently asked questions about FLUX.1 schnell

How much VRAM does FLUX.1 schnell need?

About 13.1 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 schnell on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FLUX.1 schnell GGUF?

It depends on the quant: Q4_0 is 10.0 GB, Q4_0 is 10.2 GB, Q4_1 is 11.3 GB, Q8_0 is 18.5 GB, Q8_0 is 18.6 GB, file is 34.3 GB.

Where can I download FLUX.1 schnell GGUF?

The files are on Hugging Face in the gpustack/FLUX.1-schnell-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 schnell 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.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Flux models

All Flux →

Other medium models

All medium models →