Persephone Flux 2.0 Q8 needs about 14.7 GB of memory at Q8_0 (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU.
Persephone Flux 2.0 Q8 – 11.9B parameter image generation model
Persephone Flux 2.0 Q8 is a GGUF quantized version of the Flux family model. It contains 11.9 billion parameters and is optimized for stable‑diffusion.cpp. The model supports image generation with a 8k context size.
Good at
- High‑fidelity image generation
- Fast inference with Q8 quantization
- Stable‑diffusion.cpp compatibility
Limits
- Requires separate VAE, CLIP, and T5‑XXL files
- No vision support in this quant
- License is non‑commercial
Best for
- Creative image generation
- Rapid prototyping with stable‑diffusion.cpp
- Low‑latency inference on GPUs
Who it’s for. Developers and researchers who need a compact, high‑quality image generation model for stable‑diffusion.cpp workflows. The model is suitable for those who can provide the required auxiliary files and comply with the non‑commercial license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → |
For 12.71 GB file size, the Q8_0 quantization requires about 14.7 GB of VRAM at 8k context. If you have 16 GB VRAM, this quant is suitable. For lower VRAM, consider a lower‑bit quant if available.
What GPU do you need for Persephone Flux 2.0 Q8?
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 Q8_0 (12.7 GB file, about 14.7 GB in use).
Which Persephone Flux 2.0 Q8 quant should you choose?
Q8_0 (12.7 GB) is the middle option in this repository. 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
Source
Frequently asked questions about Persephone Flux 2.0 Q8
How much VRAM does Persephone Flux 2.0 Q8 need?
About 14.7 GB at Q8_0 with an 8K context window. That is the 12.7 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 Persephone Flux 2.0 Q8 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Persephone Flux 2.0 Q8 GGUF?
It depends on the quant: Q8_0 is 12.7 GB.
Where can I download Persephone Flux 2.0 Q8 GGUF?
The files are on Hugging Face in the pyys/Persephone-Flux-2.0-Q8-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 Persephone Flux 2.0 Q8 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 Persephone Flux 2.0 Q8 on 8 GB VRAM?
No, the model requires approximately 14.7 GB of VRAM at 8k context, which exceeds 8 GB.
What auxiliary files are needed?
Separate VAE, CLIP, and T5‑XXL files are required for stable‑diffusion.cpp usage.
Is this model suitable for commercial use?
The license is FLUX.1 [dev] Non‑Commercial, so it is not for commercial deployment.