metadata
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
- gguf
- flux
- text-to-image
- imatrix
Support
- ComfyUI-GGUF: TBC
- Forge: TBC
- stable-diffusion.cpp: llama.cpp Feature-matrix
Bravo
Combined imatrix multiple images 25 and 50 steps q8 euler
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| - | IQ1_S | - | TBC |
Alpha
Simple imatrix: 512x512 single image 8/20 steps q3_K_S euler data: load_imatrix: loaded 314 importance matrix entries from imatrix.dat computed on 7 chunks
Using llama.cpp quantize cae9fb4.
Experimental from q8
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| flux1-dev-IQ1_S.gguf | IQ1_S | 2.45GB | TBC |
| - | IQ1_M | - | broken |
| flux1-dev-TQ1_0.gguf | TQ1_0 | 2.63GB | TBC |
| flux1-dev-TQ2_0.gguf | TQ2_0 | 3.19GB | TBC |
| flux1-dev-IQ2_XXS.gguf | IQ2_XXS | 3.19GB | TBC |
| flux1-dev-IQ2_XS.gguf | IQ2_XS | 3.56GB | TBC |
| flux1-dev-IQ2_S.gguf | IQ2_S | 3.56GB | TBC |
| flux1-dev-IQ2_M.gguf | IQ2_M | 3.93GB | TBC |
| - | IQ3_XS | TBC | TBC |
| - | IQ3_S | TBC | TBC |
| - | IQ3_M | TBC | TBC |
| - | Q2_K | TBC | TBC |
| flux1-dev-Q2_K_S.gguf | Q2_K_S | 4.02GB | TBC |
| - | Q3_K | TBC | TBC |
| flux1-dev-Q3_K_S.gguf | Q3_K_S | 5.22GB | TBC |