FL

Flux.1 Dedistilled Mix Tuned fp8

FluxGGUF by wikeeyangUpdated 2024-11-29
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architecture—
Smallest quant7.5 GB
Quick answer

Flux.1 Dedistilled Mix Tuned fp8 needs about 10.6 GB of memory at Q5_1 (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 7.5 GB (Q4_1) to 12.7 GB (Q8_0).

Flux.1 Dedistilled Mix Tuned fp8 – fast, high‑quality image generation

Flux.1 Dedistilled Mix Tuned fp8 is a 11.9 billion‑parameter model based on Flux.1 Schnell and Flux-Fusion‑V2. It is optimized for quick image generation with 4‑8 steps, delivering strong prompt following and detailed, realistic outputs.

Good at

  • Fast 4‑8 step generation
  • Strong prompt fidelity
  • High image detail

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • License is other

Best for

  • Rapid prototyping of image prompts
  • Low‑step image generation
  • Fine‑tuned detail work

Who it’s for. Developers and artists who need a lightweight Flux model for quick image creation. The model is suitable for those who prefer a balance between speed and quality without extensive hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_17.5 GB 8.9 GB
Too big Get file →
Q4_17.5 GB 8.9 GB
Too big Get file →
Q5_19.0 GB 10.6 GB
Too big Get file →
Q5_19.0 GB 10.6 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_1 (file size 7.51 GB, estimated memory 8.9 GB). For 12 GB VRAM, Q5_1 (file size 8.99 GB, estimated memory 10.6 GB). For 16 GB VRAM, Q8_0 (file size 12.69 GB, estimated memory 14.7 GB). Estimates are approximate.

What GPU do you need for Flux.1 Dedistilled Mix Tuned fp8?

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 Q5_1 (9.0 GB file, about 10.6 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 Flux.1 Dedistilled Mix Tuned fp8 quant should you choose?

Q5_1 (9.0 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 Q4_1 at 7.5 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

Parameters11.9B

Source

Quantized bywikeeyang
FamilyFlux
Licenseother
Downloads (HF)1,648
Last updated2024-11-29

Frequently asked questions about Flux.1 Dedistilled Mix Tuned fp8

How much VRAM does Flux.1 Dedistilled Mix Tuned fp8 need?

About 10.6 GB at Q5_1 with an 8K context window. That is the 9.0 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 Dedistilled Mix Tuned fp8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Flux.1 Dedistilled Mix Tuned fp8 GGUF?

It depends on the quant: Q4_1 is 7.5 GB, Q4_1 is 7.5 GB, Q5_1 is 9.0 GB, Q5_1 is 9.0 GB, Q8_0 is 12.7 GB, Q8_0 is 12.7 GB.

Where can I download Flux.1 Dedistilled Mix Tuned fp8 GGUF?

The files are on Hugging Face in the wikeeyang/Flux.1-Dedistilled-Mix-Tuned-fp8 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 Dedistilled Mix Tuned fp8 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 Flux.1 Dedistilled Mix Tuned fp8 on 8 GB VRAM?

Yes, the Q4_1 quantized version requires about 8.9 GB of VRAM at 8‑k context, which fits within 8 GB with some overhead.

Does this model support text‑to‑image only?

Yes, the model is designed for image generation and requires text encoders and VAE for full functionality.

Is there a license restriction?

The model is released under an 'other' license; check the repository for specific terms before commercial use.

Similar models

Browse all →

More from wikeeyang

All by wikeeyang →

More Flux models

All Flux →

Other medium models

All medium models →