FL

Hyper FLUX.1 dev

FluxGGUF by martintomovUpdated 2024-10-23
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architectureflux
Smallest quant4.0 GB
Quick answer

Hyper FLUX.1 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 20 quants, from 4.0 GB (Q2_K) to 12.7 GB (Q8_0).

Hyper FLUX.1 dev – a 11.9B parameter Flux model in GGUF format

Hyper FLUX.1 dev is a 11.9 billion parameter Flux model converted to GGUF. It is a direct conversion of black-forest-labs/FLUX.1-dev merged with ByteDance/Hyper-Flux. The model is available in multiple quantizations for different memory budgets.

Good at

  • Image generation
  • Text‑to‑image synthesis
  • Custom prompt control

Limits

  • No vision support in the GGUF conversion
  • License type is other, not specified
  • Context length not provided

Best for

  • Local image generation on a single GPU
  • Rapid prototyping of diffusion pipelines
  • ComfyUI custom node integration

Who it’s for. Developers and researchers who need a lightweight Flux model for local inference. The model is suitable for users with limited GPU memory who can choose an appropriate quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.0 GB 5.0 GB
Fits Get file →
Q2_K4.0 GB 5.0 GB
Fits Get file →
Q3_K_M4.3 GB 5.3 GB
Fits Get file →
Q5_04.3 GB 5.3 GB
Fits Get file →
Q5_14.3 GB 5.3 GB
Fits Get file →
Q5_K_M4.3 GB 5.3 GB
Fits Get file →
Q6_K4.3 GB 5.3 GB
Fits Get file →
Q8_04.3 GB 5.3 GB
Fits Get file →
Q3_K_M5.4 GB 6.5 GB
Fits Get file →
Q4_06.8 GB 8.1 GB
Too big Get file →
Q4_06.8 GB 8.1 GB
Too big Get file →
Q4_K_M6.9 GB 8.3 GB
Too big Get file →
Q4_K_M6.9 GB 8.3 GB
Too big Get file →
Q4_17.5 GB 8.9 GB
Too big Get file →
Q4_17.5 GB 8.9 GB
Too big Get file →
Q5_08.3 GB 9.8 GB
Too big Get file →
Q5_K_M8.4 GB 9.9 GB
Too big Get file →
Q5_19.0 GB 10.6 GB
Too big Get file →
Q6_K9.9 GB 11.5 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 6.8 GB, estimated memory 8.1 GB). For 12 GB VRAM, Q4_K_M (6.93 GB, 8.3 GB) or Q5_0 (8.28 GB, 9.8 GB). For 16 GB VRAM, Q5_K_M (8.42 GB, 9.9 GB) or Q6_K (9.85 GB, 11.5 GB). Memory estimates are approximate.

What GPU do you need for Hyper FLUX.1 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: the best quant that fits is Q3_K_M (4.3 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (5.4 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.9 GB file, about 11.5 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 Hyper FLUX.1 dev quant should you choose?

Q4_K_M is the usual starting point for Hyper FLUX.1 dev: it balances file size and quality well. Here it is a 6.9 GB file.

The Q8_0 file is 4.3 GB, about 0.6 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 4.0 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
Parameters11.9B

Source

Quantized bymartintomov
FamilyFlux
Licenseother
Downloads (HF)1,505
Last updated2024-10-23

Frequently asked questions about Hyper FLUX.1 dev

How much VRAM does Hyper FLUX.1 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 Hyper FLUX.1 dev on an 8 GB GPU?

Yes, with Q3_K_M: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hyper FLUX.1 dev GGUF?

It depends on the quant: Q2_K is 4.0 GB, Q2_K is 4.0 GB, Q3_K_M is 4.3 GB, Q5_0 is 4.3 GB, Q5_1 is 4.3 GB, Q5_K_M is 4.3 GB and 14 more.

Where can I download Hyper FLUX.1 dev GGUF?

The files are on Hugging Face in the martintomov/Hyper-FLUX.1-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 Hyper FLUX.1 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.

Can I run Hyper FLUX.1 dev on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 8.1 GB of VRAM.

Does the model support vision tasks?

No, the GGUF conversion does not include vision support.

Where can I find the model files?

Place the GGUF files in `ComfyUI/models/unet` for use with the ComfyUI‑GGUF custom node.

Other GGUFs of FLUX.1-dev

Similar models

Browse all →

More from martintomov

All by martintomov →

More Flux models

All Flux →

Other medium models

All medium models →