FL

FLUX.1 schnell

FluxGGUF by second-stateUpdated 2024-09-25
Download on Hugging Face
Parameters84M
Context—
Layers—
Architecture—
Smallest quant0.1 GB
Quick answer

FLUX.1 schnell needs about 4.6 GB of memory at Q5_1 (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 0.1 GB (Q8_0) to 23.8 GB (F16).

FLUX.1 schnell – a lightweight Flux model in GGUF format

FLUX.1 schnell is a 0.0838 billion‑parameter model from the Flux family. It is available in multiple GGUF quantizations and licensed under Apache‑2.0. The model supports text‑to‑image generation with a small context size.

Good at

  • Fast inference on modest GPUs
  • Low memory footprint in low‑bit quantizations
  • Text‑to‑image generation

Limits

  • No vision support in the provided GGUFs
  • Requires 8 k context for memory estimates
  • Large quantizations need more than 10 GB VRAM

Best for

  • Rapid prototyping of image generation
  • Running on edge devices with limited VRAM
  • Generating images from short prompts

Who it’s for. Developers and researchers who need a compact Flux model for quick experimentation. The model is suitable for local inference on consumer GPUs and for integration into lightweight pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.2 GB 0.7 GB
Fits Get file →
F160.2 GB 0.8 GB
Fits Get file →
Q2_K1.6 GB 2.3 GB
Fits Get file →
Q3_K2.1 GB 2.9 GB
Fits Get file →
Q4_02.8 GB 3.6 GB
Fits Get file →
Q4_K2.8 GB 3.6 GB
Fits Get file →
Q5_03.4 GB 4.3 GB
Fits Get file →
Q5_13.7 GB 4.6 GB
Fits Get file →
Q8_05.2 GB 6.3 GB
Fits Get file →
Q4_06.7 GB 8.0 GB
Tight Get file →
Q4_17.4 GB 8.8 GB
Too big Get file →
Q5_08.2 GB 9.7 GB
Too big Get file →
Q5_18.9 GB 10.5 GB
Too big Get file →
F169.8 GB 11.5 GB
Too big Get file →
Q8_012.6 GB 14.7 GB
Too big Get file →
F1623.8 GB 27.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 2.75 GB, memory 3.6 GB). For 12 GB VRAM, Q5_0 (file size 3.36 GB, memory 4.3 GB) or Q4_1 (file size 7.43 GB, memory 8.8 GB). For 16 GB VRAM, Q8_0 (file size 5.2 GB, memory 6.3 GB) or Q5_1 (file size 8.92 GB, memory 10.5 GB).

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: the best quant that fits is Q4_K (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_1 (3.7 GB file, about 4.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.8 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.6 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.6 GB file, about 14.7 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (23.8 GB file, about 27.1 GB in use).

Which FLUX.1 schnell quant should you choose?

Q5_1 (3.7 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.

If memory is tight, the smallest file is Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters84M

Source

Quantized bysecond-state
FamilyFlux
Licenseapache-2.0
Downloads (HF)6,318
Last updated2024-09-25

Frequently asked questions about FLUX.1 schnell

How much VRAM does FLUX.1 schnell need?

About 4.6 GB at Q5_1 with an 8K context window. That is the 3.7 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?

Yes, with Q4_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.2 GB, F16 is 0.2 GB, Q2_K is 1.6 GB, Q3_K is 2.1 GB, Q4_0 is 2.8 GB and 11 more.

Where can I download FLUX.1 schnell GGUF?

The files are on Hugging Face in the second-state/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.

Can I run FLUX.1 schnell on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 3.6 GB of VRAM at 8 k context.

Does FLUX.1 schnell support vision tasks?

No, the provided GGUFs do not include vision capabilities.

Other GGUFs of FLUX.1-schnell

Similar models

Browse all →

More from second-state

All by second-state →

More Flux models

All Flux →

Other tiny models

All tiny models →