FL

flux2

FluxGGUF by arcticlatentUpdated 2025-11-28
Download on Hugging Face
Parameters32.2B
Context—
Layers—
Architectureflux
Smallest quant11.0 GB
Quick answer

flux2 needs about 21.5 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 11.0 GB (Q2_K) to 34.5 GB (Q8_0).

flux2 is a 32.2B-parameter Flux model in GGUF format, quantized by arcticlatent. The repository has 6 quant files, from 11.0 GB (Q2_K) to 34.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.0 GB 12.8 GB
Too big Get file →
Q3_K_M14.5 GB 16.7 GB
Too big Get file →
Q4_K_M18.7 GB 21.5 GB
Too big Get file →
Q5_K_M22.7 GB 25.9 GB
Too big Get file →
Q6_K26.7 GB 30.4 GB
Too big Get file →
Q8_034.5 GB 39.1 GB
Too big Get file →

What GPU do you need for flux2?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (11.0 GB file, about 12.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (18.7 GB file, about 21.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.5 GB file, about 39.1 GB in use).

Which flux2 quant should you choose?

Q4_K_M is the usual starting point for flux2: it balances file size and quality well. Here it is a 18.7 GB file.

The Q8_0 file is 34.5 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 Q2_K at 11.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters32.2B

Source

Quantized byarcticlatent
FamilyFlux
Downloads (HF)16
Last updated2025-11-28

Frequently asked questions about flux2

How much VRAM does flux2 need?

About 21.5 GB at Q4_K_M with an 8K context window. That is the 18.7 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 flux2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of flux2 GGUF?

It depends on the quant: Q2_K is 11.0 GB, Q3_K_M is 14.5 GB, Q4_K_M is 18.7 GB, Q5_K_M is 22.7 GB, Q6_K is 26.7 GB, Q8_0 is 34.5 GB.

Where can I download flux2 GGUF?

The files are on Hugging Face in the arcticlatent/flux2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from arcticlatent

All by arcticlatent →

More Flux models

All Flux →

Other medium models

All medium models →