FL

Flux3 PE GGUF Comfy

FluxGGUF by t8starUpdated 2026-10-18
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant5.6 GB
Quick answer

Flux3 PE GGUF Comfy needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_K_M) to 5.6 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Flux3 PE GGUF Comfy – prompt enhancement for Flux 3 image generation

Flux3 PE GGUF Comfy is a Q4_K_M quantized model derived from Flux 3 Image Klein. It expands short image requests into detailed prompts for text-to-image, editing, and layout tasks. The model supports up to 10 reference images and bounding boxes.

Good at

  • Prompt upsampling for Flux 3
  • Text-to-image prompt generation
  • Layout constraint handling

Limits

  • Requires 7.2 GB VRAM at 8k context
  • No vision support beyond prompt enhancement
  • License is other

Best for

  • ComfyUI prompt enhancement workflows
  • Image generation pipelines needing detailed prompts
  • Editing with reference images

Who it’s for. Users of ComfyUI who need a lightweight prompt enhancer for Flux 3 image models. It is suitable for artists and developers working with text-to-image or editing workflows that rely on Flux 3.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →

For 8 GB VRAM, use the Q4_K_M quantized file (5.63 GB). It requires approximately 7.2 GB of VRAM at 8k context. If more memory is available, the same quant is optimal; no other quants are provided.

What GPU do you need for Flux3 PE GGUF Comfy?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).

Which Flux3 PE GGUF Comfy quant should you choose?

Q4_K_M is the usual starting point for Flux3 PE GGUF Comfy: it balances file size and quality well. Here it is a 5.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byt8star
FamilyFlux
Licenseother
Downloads (HF)2,036
Last updated2026-10-18

Frequently asked questions about Flux3 PE GGUF Comfy

How much VRAM does Flux3 PE GGUF Comfy need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Flux3 PE GGUF Comfy on an 8 GB GPU?

Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Flux3 PE GGUF Comfy GGUF?

It depends on the quant: Q4_K_M is 5.6 GB, Q4_K_M is 5.6 GB.

What context length does Flux3 PE GGUF Comfy support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Flux3 PE GGUF Comfy GGUF?

The files are on Hugging Face in the t8star/Flux3-PE-GGUF-Comfy repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Flux3 PE GGUF Comfy 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 Flux3 PE GGUF on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 7.2 GB VRAM at 8k context, which fits within an 8 GB budget.

Does this model support vision tasks?

No, it only enhances prompts; image generation is handled by separate diffusion, text‑encoder and VAE weights.

What file size should I download?

Each Q4_K_M model file is 5.63 GB; the F16 projector is 0.92 GB.

Other GGUFs of flux-3-image-klein-pup

Similar models

Browse all →

More from t8star

All by t8star →

More Flux models

All Flux →

Other small models

All small models →