Check my GPU →

FLUX.1 Fill [dev] on 16 GB of VRAM

Yes, but only just: Q8_0 leaves 0.7 GB free on 16 GB. The inpainting and outpainting model from the FLUX.1 Tools release. Same 12B size class as FLUX.1 dev.

Image model · 12BAny 16 GB GPUData 2026-10-01
Runs well
Yes, just.

Q8_0 (12.7 GB) fits with only 0.7 GB to spare (about 15.3 GB of 16 GB).

Best fileQ8_0
File size12.7 GB
VRAM needed~15.3 GB
System RAM32 GB+
Memory map · 16 GB GPU15.3 GB / 16 GB
08 GB16 GB
Weights Q8_0 · 12.7 GBWorking memory · 1.8 GBReserve · 0.8 GBFree · 0.7 GB

01What to download

PartFileFolderSize
Modelflux1-fill-dev-Q8_0.gguf
Q8_0 · YarvixPA/FLUX.1-Fill-dev-GGUF
models/unet12.7 GBDownload →
Text encodert5xxl_fp8_e4m3fn.safetensors
T5-XXL FP8 · comfyanonymous/flux_text_encoders
models/text_encoders4.9 GBDownload →
Text encoderclip_l.safetensors
CLIP-L · comfyanonymous/flux_text_encoders
models/text_encoders0.2 GBDownload →
VAEae.safetensors
FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged
models/vae0.3 GBDownload →
Total download · keep about the same free on disk18.2 GB

Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.

02Every file, on 16 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · black-forest-labs
23.8 GB26.4 GB10.4 GB too bigthe original weightsHugging Face →
Q8_0 ←
GGUF · YarvixPA
12.7 GB15.3 GBfits · 0.7 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · YarvixPA
9.9 GB12.5 GBfits · 3.5 GB sparevery close to the originalHugging Face →
Q5_K_S
GGUF · YarvixPA
8.3 GB10.9 GBfits · 5.1 GB spareclose; small differences in fine detailHugging Face →
Q4_K_S
GGUF · YarvixPA
6.8 GB9.4 GBfits · 6.6 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_S
GGUF · YarvixPA
5.2 GB7.8 GBfits · 8.2 GB sparenoticeable loss of detailHugging Face →

“Needed” adds 1.8 GB of working memory for FLUX.1 Fill and a 0.8 GB reserve. Sizes 2026-10-01.